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

    Neuronpedia

    INDEX
    Explanations

    attributes related to structure and syntax in data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encu
    -0.32
    GA
    -0.23
    DO
    -0.23
    NOTE
    -0.22
    http
    -0.21
    https
    -0.21
    º
    -0.21
    G
    -0.21
    ⠀
    -0.21
     olyan
    -0.19
    POSITIVE LOGITS
    ValueStyle
    0.91
    ſelben
    0.81
     виправивши
    0.79
     ſeines
    0.78
    往下閱讀
    0.78
    principalColumn
    0.77
     Menſchen
    0.77
     パンチラ
    0.76
     erſten
    0.76
    ロウィン
    0.75
    Act Density 0.000%

    No Known Activations