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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or statistics

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

    numbers, punctuation, and code markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.84
    ValueStyle
    -0.73
    Tikang
    -0.71
    Chham
    -0.70
     ujednoznacz
    -0.69
    rungsseite
    -0.69
    ScopeManager
    -0.68
    IntoConstraints
    -0.68
     MainAxisSize
    -0.66
    ViewImports
    -0.65
    POSITIVE LOGITS
     impac
    0.36
    !
    0.33
    Today
    0.32
     Eventually
    0.31
    ).
    0.31
     معرف
    0.29
     ,
    0.29
    scaled
    0.29
     regenerated
    0.29
    ED
    0.29
    Act Density 0.016%

    No Known Activations