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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Soy
    -0.07
     Sof
    -0.06
     DIY
    -0.06
     separated
    -0.06
     Futures
    -0.06
    鬼
    -0.06
     сал
    -0.06
     �
    -0.06
     Scale
    -0.06
    StateException
    -0.06
    POSITIVE LOGITS
    AMY
    0.07
    VEC
    0.06
    _TICK
    0.06
     Bay
    0.06
    Body
    0.06
    aven
    0.06
    merc
    0.06
    coh
    0.06
    ावर
    0.06
    ریب
    0.06
    Act Density 0.034%

    No Known Activations