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

    Neuronpedia

    INDEX
    Explanations

    terms related to competitions and eliminations

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

    ranking and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    曖昧さ回避
    -0.49
    awtextra
    -0.47
    featureID
    -0.45
    MessageOf
    -0.41
     supra
    -0.41
    aarrggbb
    -0.39
    IsMutable
    -0.38
    :+:
    -0.38
    onOptions
    -0.38
    cestry
    -0.38
    POSITIVE LOGITS
     judiciaire
    0.44
    UnknownFieldSet
    0.40
     mahdol
    0.36
    bleven
    0.36
    IBER
    0.36
    MessageTagHelper
    0.35
    endfor
    0.35
     αντί
    0.35
     denk
    0.35
     Elimination
    0.35
    Act Density 0.185%

    No Known Activations