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

    Neuronpedia

    INDEX
    Explanations

    roles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standard
    0.63
     spacious
    0.57
     staples
    0.57
    %',
    0.56
    <0x0D>
    0.56
     chronological
    0.55
                              
    0.55
     any
    0.55
    NaN
    0.55
     \
    0.54
    POSITIVE LOGITS
     hinting
    0.81
     hint
    0.80
    hint
    0.75
     Кстати
    0.73
     enfat
    0.72
     consape
    0.71
    透露
    0.71
     ReturnVal
    0.71
     verhindern
    0.70
     மறை
    0.70
    Act Density 0.000%

    No Known Activations