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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms and concepts related to distribution models and statistical analysis

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

    Plural nouns and acronyms

    np_acts-logits-general · gemini-2.0-flash

    plural nouns like indices, boards, cams, juries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    smöglichkeiten
    -0.52
     neler
    -0.51
    weds
    -0.49
    mbros
    -0.49
     strán
    -0.49
     között
    -0.47
     Lordships
    -0.47
     OMITBAD
    -0.47
     esbo
    -0.47
    ξεις
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    0.83
     nahilalakip
    0.80
    apimachinery
    0.72
    afficheront
    0.72
    ArrowToggle
    0.71
    aarrggbb
    0.69
    ⓧ
    0.67
     esternos
    0.67
     oprot
    0.67
     فريبيس
    0.63
    Act Density 0.828%

    No Known Activations