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

    Neuronpedia

    INDEX
    Explanations

    without or non-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tovar
    0.45
    voicing
    0.44
    я
    0.44
    ково
    0.43
    си
    0.42
    тали
    0.42
    tale
    0.42
    обра
    0.42
    ва
    0.41
    тики
    0.41
    POSITIVE LOGITS
     Qb
    0.49
     traduction
    0.47
     Traditional
    0.46
     définition
    0.46
     determinadas
    0.46
     Remix
    0.44
     متنوع
    0.44
    二级
    0.44
     plusieurs
    0.43
    JQ
    0.43
    Act Density 0.001%

    No Known Activations