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

    Neuronpedia

    INDEX
    Explanations

    references to formal statistical analyses or parameters

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

    Text within brackets ( [] )

    np_acts-logits-general · gemini-2.0-flash

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.69
     hinweg
    -0.52
    UnifiedTopology
    -0.51
    MessageState
    -0.48
     disambiguazione
    -0.46
     Normdatei
    -0.46
     indisponible
    -0.46
     CURIAM
    -0.46
    новниш
    -0.45
    tonode
    -0.44
    POSITIVE LOGITS
     ethical
    0.45
    Демографія
    0.41
     Mul
    0.41
     fire
    0.40
     dre
    0.40
     Muse
    0.40
    รก
    0.40
     fir
    0.40
     burs
    0.40
     equi
    0.39
    Act Density 0.377%

    No Known Activations