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

    Neuronpedia

    INDEX
    Explanations

    Code imports/includes

    np_max-act · gemini-2.0-flash

    The neuron activates on C/Objective-C/Python include or import directives (lines bringing in external headers/modules).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ولوج
    -0.07
    นก
    -0.07
    _TRNS
    -0.06
    ガ
    -0.06
    RelativeTo
    -0.06
     ＿
    -0.06
     Watts
    -0.06
    ancell
    -0.06
    hawk
    -0.06
     autoFocus
    -0.05
    POSITIVE LOGITS
     dish
    0.07
    ायन
    0.07
    ขณะ
    0.06
    Mar
    0.06
     dreaded
    0.06
     veterans
    0.06
    elsing
    0.06
     лицо
    0.06
     Latest
    0.06
     means
    0.06
    Act Density 0.023%

    No Known Activations