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

    Neuronpedia

    INDEX
    Explanations

    Mono

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Suc
    -0.07
    (ExpectedConditions
    -0.06
    Pot
    -0.06
    ับการ
    -0.06
     stale
    -0.06
    Dock
    -0.06
    .red
    -0.06
    Breaking
    -0.06
    Mon
    -0.06
    /Search
    -0.06
    POSITIVE LOGITS
    [vertex
    0.07
     حالت
    0.07
    имв
    0.06
    _LIGHT
    0.06
    sem
    0.06
     egal
    0.06
    иф
    0.06
     khác
    0.06
     기타
    0.06
     그냥
    0.06
    Act Density 0.001%

    No Known Activations