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

    Neuronpedia

    INDEX
    Explanations

    terms related to variations and permutations in data

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

    varied forms or occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firme
    -0.35
    TKey
    -0.35
    AnchorTagHelper
    -0.35
     leiding
    -0.33
    整
    -0.31
     Bomba
    -0.31
    SUZ
    -0.31
    publicain
    -0.31
     initData
    -0.31
     Trous
    -0.31
    POSITIVE LOGITS
     variations
    1.01
    variations
    0.95
     variation
    0.95
    Variations
    0.93
     Variations
    0.91
    variation
    0.89
    Variation
    0.84
     Variation
    0.83
    Variante
    0.77
     variaciones
    0.76
    Act Density 0.175%

    No Known Activations