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

    Neuronpedia

    INDEX
    Explanations

    technical terms and definitions, particularly related to programming and logical constructs

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

    valid reason or defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tä
    -0.39
    aarrggbb
    -0.37
     petit
    -0.36
     sy
    -0.36
    enterOuterAlt
    -0.35
     petits
    -0.34
    帖最后由
    -0.33
    Tä
    -0.33
    OuterAlt
    -0.32
     safety
    -0.32
    POSITIVE LOGITS
    principalColumn
    0.63
    Tembelea
    0.55
     myſelf
    0.54
     themſelves
    0.52
     desmotivaciones
    0.48
     menuItem
    0.47
    zeitige
    0.47
    IntoConstraints
    0.47
    DockStyle
    0.46
    Datuak
    0.46
    Act Density 0.314%

    No Known Activations