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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that are comparative, superlative, or otherwise indicate a degree or quantity

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.62
     تانيه
    -0.55
    //
    -0.54
    extAlignment
    -0.53
     cherchés
    -0.52
     laten
    -0.52
    styleUrls
    -0.51
     lower
    -0.51
    __':
    -0.51
     Roskov
    -0.50
    POSITIVE LOGITS
    featureID
    0.57
    StreetMap
    0.54
    <bos>
    0.50
    woff
    0.49
    üch
    0.49
     HasFactory
    0.48
    tecla
    0.46
    verifyException
    0.45
     according
    0.45
     kaynağından
    0.45
    Act Density 2.064%

    No Known Activations