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

    Neuronpedia

    INDEX
    Explanations

    structures or components related to code or programming syntax

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

    Code or data examples

    np_acts-logits-general · gemini-2.0-flash

    `nm` and `nmgp` codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ogaster
    -0.66
    -0.63
     malades
    -0.58
     geométrico
    -0.58
     Preguntas
    -0.56
     Mexicano
    -0.56
     poichè
    -0.55
     métallique
    -0.55
     sexuales
    -0.54
    Referințe
    -0.54
    POSITIVE LOGITS
    nmgp
    0.75
    NM
    0.63
     nm
    0.63
    opc
    0.61
    nm
    0.60
     NM
    0.59
    !*\
    0.58
    LookAnd
    0.57
     Nm
    0.54
    cun
    0.54
    Act Density 0.022%

    No Known Activations