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

    Neuronpedia

    INDEX
    Explanations

    sentences describing research methods and results.

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.82
     Efq
    -0.81
    帖最后由
    -0.79
     houſe
    -0.78
     poffe
    -0.74
     мәкал
    -0.73
     Houſe
    -0.73
    oredCriteria
    -0.71
     itſelf
    -0.70
     Monfieur
    -0.70
    POSITIVE LOGITS
    Hauptartikel
    0.46
     parent
    0.44
    cshtml
    0.43
    гла
    0.42
    param
    0.42
    ներ
    0.42
    rsiniz
    0.42
     dad
    0.41
     titul
    0.40
     involve
    0.40
    Act Density 0.536%

    No Known Activations