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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or numerical data

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

    lists, numbers, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.57
     мәкал
    -0.54
     Roskov
    -0.52
    хьтан
    -0.48
    ViewFeatures
    -0.47
    EndContext
    -0.47
    featureID
    -0.46
     defaultstate
    -0.46
     Biôgrafia
    -0.45
    SequentialGroup
    -0.44
    POSITIVE LOGITS
    Taylor
    0.46
    Carly
    0.45
     disponibilités
    0.45
    grà
    0.44
    LOAT
    0.44
    𑄴
    0.43
    Virgil
    0.43
    ſicht
    0.43
    UND
    0.43
    𑄮
    0.43
    Act Density 0.332%

    No Known Activations