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

    Neuronpedia

    INDEX
    Explanations

    primarilyeast combined with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeżeli
    0.44
     closets
    0.42
    oryt
    0.41
    Suff
    0.41
    anym
    0.40
    Jeśli
    0.40
    ോ
    0.40
    Eligibility
    0.40
    IsDir
    0.39
     толькі
    0.39
    POSITIVE LOGITS
     migrate
    0.44
     كبير
    0.42
     rů
    0.42
    arul
    0.41
     train
    0.40
     peter
    0.40
     blade
    0.39
     prema
    0.39
     kekurangan
    0.39
    versa
    0.38
    Act Density 0.002%

    No Known Activations