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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on conditional “If…” disclaimers (e.g. “If a question…,” “If I don’t know…”) indicating uncertainty or caveats.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    所以
    -0.06
     Περι
    -0.06
    -0.06
     قرار
    -0.06
     پار
    -0.06
    デ
    -0.06
    泰
    -0.06
    statement
    -0.06
     застосування
    -0.06
     спад
    -0.06
    POSITIVE LOGITS
     Jackets
    0.07
     fim
    0.06
    ΗΣ
    0.06
     Mansion
    0.06
     Courts
    0.06
     Deals
    0.06
    DebugEnabled
    0.06
     comprehensive
    0.06
    _instruction
    0.06
    σσα
    0.06
    Act Density 0.009%

    No Known Activations