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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting within complex written content

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

    Code, math, or obscure technical language

    np_acts-logits-general · gemini-2.0-flash

    deno or, breast, abusive, estoppel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
    AutoScaleMode
    -0.54
    AndEndTag
    -0.52
    EndContext
    -0.50
    IntoConstraints
    -0.49
    PerformLayout
    -0.47
    әрмәләр
    -0.46
    TypedDataSet
    -0.46
    printStackTrace
    -0.45
     initComponents
    -0.45
    POSITIVE LOGITS
     Grüsse
    0.44
    thoven
    0.43
    */),
    0.41
    ɕ
    0.41
    Few
    0.41
    NECT
    0.40
    apimachinery
    0.40
    ❉
    0.40
    PostBack
    0.39
    abetes
    0.39
    Act Density 1.271%

    No Known Activations