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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    The neuron responds to words used when asking the user to clarify or provide more context (e.g., “asking,” “clarify,” “provide more context”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    いている
    -0.09
    .SetToolTip
    -0.07
    _repr
    -0.07
     政
    -0.07
    ‍
    -0.06
     evolve
    -0.06
     presentation
    -0.06
    ться
    -0.06
     celui
    -0.06
    _Store
    -0.06
    POSITIVE LOGITS
     IPAddress
    0.07
     monopol
    0.06
     NEC
    0.06
     yen
    0.06
    CallBack
    0.06
     oppress
    0.06
    (define
    0.06
    ondrous
    0.06
     isa
    0.06
    /lic
    0.06
    Act Density 0.011%

    No Known Activations