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

    Neuronpedia

    INDEX
    Explanations

    why followed by explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powied
    1.29
    ،
    1.28
     взя
    0.94
     consistente
    0.90
    、
    0.89
     restitu
    0.86
    u
    0.83
     neutrino
    0.82
    ，「
    0.81
     traduc
    0.80
    POSITIVE LOGITS
    ك
    1.35
    ,
    1.29
    .
    1.23
    ת
    1.17
    на
    1.14
    ב
    1.10
    נ
    1.09
    고
    1.08
    จะ
    1.07
    ат
    1.06
    Act Density 0.140%

    No Known Activations