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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and titles, particularly in scientific and historical contexts

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

    proper nouns and technical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.33
     peran
    -0.31
     ويكيپيديا
    -0.30
     vainilla
    -0.29
     manteniendo
    -0.27
     kentang
    -0.27
    Còn
    -0.27
     prefier
    -0.27
     sure
    -0.26
     cuanto
    -0.26
    POSITIVE LOGITS
    ſelf
    0.77
     ſche
    0.77
    featureID
    0.76
     ſch
    0.76
     ſta
    0.75
    ItemBackground
    0.73
    ſchaft
    0.73
     Houſe
    0.72
     ―――――
    0.72
     Majefty
    0.71
    Act Density 1.714%

    No Known Activations