Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    definition, specification

    np_max-act · gemini-2.0-flash

    code examples for creating context managers related to resource management.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on phrases indicating that a value (like a file path or filename) is supplied by the user, e.g. “provided by the user.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pellets
    -0.07
     Mol
    -0.06
    eyle
    -0.06
    _dispatch
    -0.06
    610
    -0.06
    ยะ
    -0.06
     molecules
    -0.06
    _FINAL
    -0.06
    INGLE
    -0.06
     lic
    -0.06
    POSITIVE LOGITS
     слаб
    0.07
    toBeTruthy
    0.07
    .Marker
    0.07
    Popover
    0.07
    аю
    0.07
     dejar
    0.06
    طب
    0.06
     맛
    0.06
     낮
    0.06
    _CONT
    0.06
    Act Density 0.041%

    No Known Activations