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

    Neuronpedia

    INDEX
    Explanations

    story ideas and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %),
    0.50
    Assume
    0.46
    \%),
    0.46
    specificity
    0.45
    latitude
    0.44
    \%,
    0.43
    Instit
    0.42
     sayıda
    0.42
    )、
    0.42
     recensement
    0.42
    POSITIVE LOGITS
     **
    0.60
     Example
    0.55
     Sample
    0.52
    </h2>
    0.52
     AVAILABLE
    0.52
     Would
    0.48
     Where
    0.47
     **/
    0.47
    ↵↵
    0.46
     Cheers
    0.46
    Act Density 0.017%

    No Known Activations