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

    Neuronpedia

    INDEX
    Explanations

    code identifiers, keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಥ
    0.34
    ா
    0.34
    𒋼
    0.33
     н
    0.33
    wxT
    0.32
     descricao
    0.32
    зец
    0.32
    ্দের
    0.32
     maniak
    0.32
    ﺪ
    0.31
    POSITIVE LOGITS
    if
    0.35
    0.33
    ided
    0.31
    0.31
    まず
    0.30
    %
    0.30
    rept
    0.30
    inkle
    0.30
    همه
    0.30
    0.29
    Act Density 0.021%

    No Known Activations