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

    Neuronpedia

    INDEX
    Explanations

    references to processes being attempted or in progress

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

    Beginning of non-English sentences

    np_acts-logits-general · gemini-2.0-flash

    foreign languages and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.71
    tvguidetime
    -0.51
    пример
    -0.51
     >=",
    -0.50
     belangrij
    -0.48
    ///</
    -0.47
    DataAnnotations
    -0.47
     assignable
    -0.47
    antaranya
    -0.46
    zaamheid
    -0.46
    POSITIVE LOGITS
    geb
    0.62
    }")
    0.62
    PrototypeOf
    0.62
    RAINT
    0.61
     अपनी
    0.59
     את
    0.58
     अपना
    0.57
    باً
    0.57
     himself
    0.56
    SharedDtor
    0.55
    Act Density 0.027%

    No Known Activations