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

    Neuronpedia

    INDEX
    Explanations

    Distillation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    empt
    -0.07
    sf
    -0.06
     lanç
    -0.06
    ignment
    -0.06
    appe
    -0.06
     please
    -0.06
    _allocation
    -0.06
     peel
    -0.06
    emption
    -0.06
     detach
    -0.06
    POSITIVE LOGITS
    笔
    0.07
    経
    0.07
     TRADE
    0.06
    _heat
    0.06
    汇
    0.06
    ServiceImpl
    0.06
     �
    0.06
     Thom
    0.06
     Farrell
    0.06
     وزار
    0.06
    Act Density 0.001%

    No Known Activations