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

    Neuronpedia

    INDEX
    Explanations

    border: 1px solid;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endere
    0.80
    ond
    0.79
    MD
    0.67
    BS
    0.66
    মে
    0.66
    Definitions
    0.65
    MS
    0.64
     Jeann
    0.64
    ále
    0.64
    oxyl
    0.63
    POSITIVE LOGITS
     comedy
    0.73
     lih
    0.67
     Cash
    0.67
     heo
    0.67
    荐
    0.66
     स्व
    0.65
     Lamborghini
    0.63
     স্বয়ং
    0.63
     cash
    0.63
     smoothly
    0.63
    Act Density 0.034%

    No Known Activations