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

    Neuronpedia

    INDEX
    Explanations

    QQ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taxa
    -0.07
    �
    -0.07
     �
    -0.07
    ↭
    -0.07
     pii
    -0.06
    曙光
    -0.06
    ໂ
    -0.06
     hangs
    -0.06
    ymax
    -0.06
     exile
    -0.06
    POSITIVE LOGITS
    _restore
    0.07
    .GridView
    0.07
     isinstance
    0.07
    _TP
    0.07
    ≤
    0.07
    nelly
    0.07
     Quantity
    0.06
    夜里
    0.06
    锓
    0.06
    pressure
    0.06
    Act Density 0.003%

    No Known Activations