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

    Neuronpedia

    INDEX
    Explanations

    starts, sets, change, energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $)$.
    0.48
     употреб
    0.43
     тех
    0.43
    зей
    0.41
    insuff
    0.41
     ').
    0.41
     procur
    0.40
    。「
    0.40
     covariate
    0.40
     заку
    0.40
    POSITIVE LOGITS
     Wohn
    0.53
     começa
    0.49
     انرژی
    0.48
    ጀም
    0.47
    আমরা
    0.46
    Set
    0.45
     পরিবর্তন
    0.44
    Change
    0.43
     শুরু
    0.43
     individuais
    0.43
    Act Density 0.108%

    No Known Activations