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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and operators

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

    mathematical sums over indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.62
    TargetException
    -0.57
     Reſ
    -0.57
    <unused43>
    -0.56
    <unused28>
    -0.56
    [@BOS@]
    -0.56
    <unused16>
    -0.56
    <unused41>
    -0.56
    <unused14>
    -0.56
    <unused8>
    -0.56
    POSITIVE LOGITS
     AssemblyCulture
    0.43
     and
    0.41
    󠁴
    0.39
    Erreferentziak
    0.36
     defaultstate
    0.33
    ̍t
    0.31
    HasIndex
    0.30
    OLOGÍA
    0.30
    ENCIÓN
    0.30
     transfieras
    0.29
    Act Density 0.104%

    No Known Activations