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

    Neuronpedia

    INDEX
    Explanations

    bullet points, lists, enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $=$
    0.77
    ``
    0.64
    format
    0.59
    Format
    0.58
    ོན་
    0.58
    ／
    0.57
     Views
    0.57
    }/${
    0.56
     $\{$
    0.56
    Restore
    0.56
    POSITIVE LOGITS
    papa
    0.73
    Papa
    0.68
    粳
    0.67
    atians
    0.66
    >*
    0.66
    সাধারণ
    0.66
    otyp
    0.65
    ướ
    0.64
     grandma
    0.64
    osos
    0.63
    Act Density 0.365%

    No Known Activations