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

    Neuronpedia

    INDEX
    Explanations

    terms related to native or indigenous characteristics and concepts

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

    native or natively implemented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.58
     برانيه
    -0.43
    konos
    -0.42
    点此举报
    -0.42
    verwijspagina
    -0.41
    ToTensor
    -0.39
    lamabad
    -0.39
    yskland
    -0.39
     chimie
    -0.37
    licante
    -0.37
    POSITIVE LOGITS
     Native
    1.01
     native
    1.00
    Native
    0.98
    native
    0.93
     natives
    0.88
     indigenous
    0.86
     nativo
    0.84
    NATIVE
    0.84
     nativa
    0.83
     Natives
    0.82
    Act Density 0.022%

    No Known Activations