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

    Neuronpedia

    INDEX
    Explanations

    Code and user input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .capitalize
    -0.08
    Responder
    -0.07
    росл
    -0.07
    ized
    -0.07
    _avail
    -0.07
    ificantly
    -0.07
    Culture
    -0.06
    ⇒
    -0.06
    尨
    -0.06
    _redis
    -0.06
    POSITIVE LOGITS
     ноч
    0.08
    օ
    0.07
     │
    0.07
    .OP
    0.07
     zIndex
    0.07
    ↰
    0.07
     Ин
    0.07
    婢
    0.07
    作息
    0.06
     borders
    0.06
    Act Density 0.049%

    No Known Activations