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

    Neuronpedia

    INDEX
    Explanations

    exit codes and error messages in script outputs

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

    exit with status code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ganado
    -0.39
     tratando
    -0.37
    seurs
    -0.37
     $("<
    -0.36
    ėja
    -0.35
    用品
    -0.35
    ยว
    -0.34
    Angeb
    -0.34
     pecados
    -0.34
     Sonn
    -0.34
    POSITIVE LOGITS
    TagMode
    0.71
    Autoritní
    0.62
    CloseOperation
    0.60
    RegressionTest
    0.58
    TintMode
    0.50
    addGap
    0.50
    ITHUB
    0.49
    HideFlags
    0.49
    הערות
    0.48
    DockStyle
    0.47
    Act Density 0.013%

    No Known Activations