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

    Neuronpedia

    INDEX
    Explanations

    questions and queries regarding understanding, practices, and implications

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

    questions about possibilities or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.35
     om
    -0.28
    en
    -0.28
     ibu
    -0.27
     kem
    -0.25
     en
    -0.25
     но
    -0.25
     rou
    -0.24
    by
    -0.24
    ,
    -0.24
    POSITIVE LOGITS
     EconPapers
    0.88
    Datuak
    0.83
    +#+#
    0.83
    SequentialGroup
    0.82
    évaluateur
    0.80
     vooz
    0.78
    tagHelperRunner
    0.77
    KommentareTeilen
    0.74
     zwiſchen
    0.74
     beſch
    0.73
    Act Density 0.061%

    No Known Activations