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

    Neuronpedia

    INDEX
    Explanations

    articles and punctuation marks that often structure news headlines

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

    Text following em dashes or hyphens

    np_acts-logits-general · gemini-2.0-flash

    punctuations followed by names/locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.80
    enumii
    -0.70
     indisponible
    -0.69
    =$?
    -0.63
    AndEndTag
    -0.61
     estekak
    -0.60
     Reverso
    -0.59
     entanto
    -0.57
    Hochspringen
    -0.57
    ('&
    -0.57
    POSITIVE LOGITS
     The
    0.70
    The
    0.63
     There
    0.60
    expandindo
    0.59
    stolic
    0.59
    At
    0.57
     At
    0.56
     For
    0.55
    ">—
    0.55
     Here
    0.55
    Act Density 0.100%

    No Known Activations