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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user actions and their implications in various contexts

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

    prevent overages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.50
    #+#
    -0.50
    Aiheesta
    -0.46
    ineno
    -0.45
    AddTagHelper
    -0.44
     ansi
    -0.44
    stalgia
    -0.44
     Majefty
    -0.44
    ništvo
    -0.42
     CreateTagHelper
    -0.42
    POSITIVE LOGITS
    Regional
    0.37
    Последние
    0.36
    endregion
    0.35
     Crucifix
    0.35
     @"/
    0.34
     juridique
    0.34
    léans
    0.33
     rates
    0.33
    了一口气
    0.33
     Murch
    0.32
    Act Density 0.099%

    No Known Activations