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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    占用
    -0.08
     Sand
    -0.07
     Bí
    -0.07
    Sink
    -0.07
    颛
    -0.07
    cin
    -0.07
     Hund
    -0.07
    Ice
    -0.07
    沙发上
    -0.06
    Gar
    -0.06
    POSITIVE LOGITS
    唤
    0.08
    盉
    0.07
     سنة
    0.07
    ا
    0.07
    微创
    0.07
    .application
    0.07
     replace
    0.07
    atron
    0.07
    .mapper
    0.07
     hygiene
    0.07
    Act Density 0.000%

    No Known Activations