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

    Neuronpedia

    INDEX
    Explanations

    references to explicit sexual acts and responses

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

    physical actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.60
    principalColumn
    -0.52
    UnusedPrivate
    -0.52
    RegressionTest
    -0.50
    MigrationBuilder
    -0.49
    GIVEREF
    -0.48
    oneofs
    -0.46
    CppMethod
    -0.45
    UrlResolution
    -0.45
    genodigd
    -0.45
    POSITIVE LOGITS
     CanadaChoose
    0.51
    enderror
    0.43
     Marken
    0.35
    GeneratedMessage
    0.34
    了一声
    0.33
    Παραπομπές
    0.33
     男子
    0.33
    RTHOOK
    0.32
     labour
    0.32
     labor
    0.32
    Act Density 0.071%

    No Known Activations