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

    Neuronpedia

    INDEX
    Explanations

    safe sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puzz
    0.69
     impatiently
    0.66
     arrog
    0.65
     premio
    0.62
     LOT
    0.60
     obliv
    0.59
     majest
    0.58
     loudly
    0.57
     polynomial
    0.57
     انه
    0.56
    POSITIVE LOGITS
     पातळी
    0.64
     рас
    0.64
    Рас
    0.64
    Ϲ
    0.63
    Caribbean
    0.61
    apses
    0.61
    Disclosure
    0.60
     स्तर
    0.60
    Provence
    0.60
     યોગ
    0.59
    Act Density 0.045%

    No Known Activations