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

    Neuronpedia

    INDEX
    Explanations

    specifications and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )，
    0.78
    )。
    0.76
    ز
    0.68
    )،
    0.64
    ;$
    0.64
    ?
    0.64
    。
    0.63
    ]";
    0.63
    𝙢
    0.61
     чувство
    0.61
    POSITIVE LOGITS
    im
    0.79
    is
    0.75
    atau
    0.70
    <0x0D>
    0.66
    ana
    0.66
    Attribute
    0.66
    ↵↵
    0.64
    Progress
    0.64
     albo
    0.64
    articolo
    0.64
    Act Density 0.018%

    No Known Activations