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

    Neuronpedia

    INDEX
    Explanations

    references to file and directory structures in computing

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

    file paths with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prohibido
    -0.40
     productivo
    -0.40
     inversiones
    -0.37
    éndolo
    -0.37
     mecánico
    -0.37
     océano
    -0.36
     verschillen
    -0.36
     mostrarse
    -0.36
     mecánica
    -0.35
     desconocido
    -0.35
    POSITIVE LOGITS
    ftagPool
    0.77
     الرياضيه
    0.77
    ArgsConstructor
    0.68
     Luxor
    0.66
     kaarangay
    0.65
     հղումներ
    0.65
     lenker
    0.65
    setVerticalGroup
    0.64
     ProtoMessage
    0.64
    VersionUID
    0.63
    Act Density 0.065%

    No Known Activations