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

    Neuronpedia

    INDEX
    Explanations

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヴ
    -0.07
    'ils
    -0.07
    mant
    -0.07
    وذ
    -0.07
    .Xml
    -0.07
     uten
    -0.07
    띰
    -0.07
    附加
    -0.07
    phi
    -0.07
    ients
    -0.07
    POSITIVE LOGITS
     narration
    0.08
     Mavericks
    0.08
     interceptions
    0.08
     компания
    0.07
    inst
    0.07
     MATCH
    0.07
    (Filter
    0.07
     QS
    0.07
    _FAILURE
    0.07
    (cat
    0.07
    Act Density 0.005%

    No Known Activations