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

    Neuronpedia

    INDEX
    Explanations

    content production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Log
    -0.08
    Arg
    -0.07
    .StackTrace
    -0.07
     scarf
    -0.07
     tired
    -0.07
    Divider
    -0.07
     λ
    -0.07
    你看
    -0.07
    .getEmail
    -0.07
    _allocated
    -0.07
    POSITIVE LOGITS
    escription
    0.07
    PLIC
    0.07
     smart
    0.07
    <typename
    0.07
     suç
    0.07
     recurs
    0.07
    национа
    0.07
    沟通
    0.07
    dbg
    0.07
    较好的
    0.07
    Act Density 0.059%

    No Known Activations