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

    Neuronpedia

    INDEX
    Explanations

    names of characters and their roles in film productions

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

    German verbs and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.67
    Билгалдахарш
    -0.66
    bandcamp
    -0.62
    KommentareTeilen
    -0.59
     Lorde
    -0.57
    writeField
    -0.50
    enment
    -0.50
    FUCK
    -0.49
     Martens
    -0.49
    Fuck
    -0.49
    POSITIVE LOGITS
     müßte
    0.71
     läßt
    0.70
     vedette
    0.69
     Moslem
    0.67
     mußte
    0.66
     muß
    0.66
     wußte
    0.65
     chofe
    0.65
     Cæsar
    0.61
     ſever
    0.61
    Act Density 0.210%

    No Known Activations