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

    Neuronpedia

    INDEX
    Explanations

    sequences of closing brackets or similar mathematical symbols

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

    math expressions and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -1.36
    yszer
    -0.57
    vény
    -0.56
    enskap
    -0.56
    je
    -0.54
    er
    -0.54
    ing
    -0.52
    ítmény
    -0.52
    묻
    -0.52
    tam
    -0.52
    POSITIVE LOGITS
    ième
    0.66
     EconPapers
    0.65
    Personensuche
    0.63
    sweise
    0.58
    iqué
    0.54
    ς
    0.52
    s
    0.50
     Cameroun
    0.48
     rodríguez
    0.48
    iterranée
    0.47
    Act Density 0.118%

    No Known Activations