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

    Neuronpedia

    INDEX
    Explanations

    sequences of whitespace or line breaks

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

    Code snippets with templates or paths

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.43
     HFILL
    -0.41
    ContentLoaded
    -0.39
    zzleHttp
    -0.36
    principalColumn
    -0.36
    böz
    -0.34
    RectangleBorder
    -0.33
    MLLoader
    -0.33
    TestingModule
    -0.33
    पया
    -0.32
    POSITIVE LOGITS
    0.57
    Petroleum
    0.56
    surface
    0.55
     Marcin
    0.55
     Verſ
    0.54
    smöglichkeiten
    0.54
     müſſen
    0.54
    ðsíða
    0.51
    MVH
    0.51
     Garmin
    0.51
    Act Density 0.044%

    No Known Activations