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

    Neuronpedia

    INDEX
    Explanations

    components that are related to media type handling in API requests

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

    block comments with '*'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zoude
    -0.81
     indígen
    -0.67
     laſſen
    -0.66
     ſei
    -0.66
     ſind
    -0.66
     Infór
    -0.63
    QMetaType
    -0.63
     niedersachsen
    -0.61
    guiente
    -0.61
     dezelve
    -0.61
    POSITIVE LOGITS
    *
    1.29
     *
    1.10
    //*
    0.78
    *,
    0.75
    *.
    0.73
    !*
    0.73
    *:
    0.71
    ///
    0.70
    *$
    0.70
    (*
    0.67
    Act Density 0.012%

    No Known Activations