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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and technical terms related to various fields

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

    Following two- or three-letter prefixes

    np_acts-logits-general · gemini-2.0-flash

    European origin words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.66
     
    -0.61
    -
    -0.61
     a
    -0.61
    .
    -0.56
     the
    -0.56
     are
    -0.56
     in
    -0.55
     involving
    -0.54
    ซ์
    -0.52
    POSITIVE LOGITS
     iſt
    0.85
     wikipagina
    0.81
     Efq
    0.79
     Anſ
    0.78
     Majefty
    0.78
     Perſ
    0.76
     Reſ
    0.75
     Italijanski
    0.74
     ſever
    0.73
    djangoproject
    0.73
    Act Density 0.577%

    No Known Activations