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

    Neuronpedia

    INDEX
    Explanations

    _param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tym
    -0.07
    int
    -0.07
     pretend
    -0.07
    我以为
    -0.07
     attorney
    -0.07
    麻
    -0.06
    Towards
    -0.06
     cf
    -0.06
    不算
    -0.06
    aut
    -0.06
    POSITIVE LOGITS
    CppCodeGenWriteBarrier
    0.08
    finance
    0.08
     devastated
    0.07
     resilience
    0.07
    (line
    0.07
    _firestore
    0.07
     Salesforce
    0.07
     strongest
    0.07
     economies
    0.07
    财富
    0.07
    Act Density 0.000%

    No Known Activations