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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copyright and restrictions on content use

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

    Copyright notices and distribution permissions

    np_acts-logits-general · gemini-2.0-flash

    distribution and permissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vol
    -0.46
     временем
    -0.43
    ple
    -0.42
    lottes
    -0.41
    Vol
    -0.40
     eleg
    -0.40
    vol
    -0.40
     Moore
    -0.39
    optional
    -0.39
    ween
    -0.39
    POSITIVE LOGITS
    UnsafeEnabled
    0.85
     للاسماء
    0.84
    endphp
    0.81
    Tikang
    0.81
    Personensuche
    0.77
    Aholisi
    0.75
     QLabel
    0.74
    Démographie
    0.74
     متعلقه
    0.72
     ExecuteAsync
    0.70
    Act Density 0.144%

    No Known Activations