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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

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

    lists of descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.39
     '
    -0.37
     “
    -0.35
    θ
    -0.35
    “
    -0.35
     θ
    -0.34
    (
    -0.34
    .
    -0.34
    posedge
    -0.33
     de
    -0.32
    POSITIVE LOGITS
    transQ
    0.98
    thschild
    0.78
    featureID
    0.75
     sumpay
    0.74
    expandindo
    0.73
     fashiola
    0.72
    CppMethod
    0.72
    нгред
    0.71
     виправивши
    0.71
    <unused8>
    0.71
    Act Density 0.044%

    No Known Activations