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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     חברי
    -0.07
    不动
    -0.07
     appreciate
    -0.07
    лы
    -0.07
     visiting
    -0.07
     Miss
    -0.07
    欣赏
    -0.06
    _MO
    -0.06
     miło
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
    .CreateDirectory
    0.08
    .SimpleDateFormat
    0.07
    汊
    0.07
     ICommand
    0.07
    ㈎
    0.07
    痃
    0.07
     Inhal
    0.06
    媒
    0.06
    GenerationStrategy
    0.06
    _baseline
    0.06
    Act Density 0.127%

    No Known Activations