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

    Neuronpedia

    INDEX
    Explanations

    aly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    犯规
    -0.08
    鬣
    -0.07
     ){
    -0.07
    赶上
    -0.07
     argent
    -0.07
    cala
    -0.07
     felony
    -0.07
    /inet
    -0.07
     isset
    -0.07
    桡
    -0.07
    POSITIVE LOGITS
    anj
    0.08
     exposes
    0.07
    HAM
    0.07
    眼里
    0.07
    ucumber
    0.07
     Femin
    0.07
    얖
    0.07
     nat
    0.07
     Mt
    0.06
    对我
    0.06
    Act Density 0.001%

    No Known Activations