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

    Neuronpedia

    INDEX
    Explanations

    classifications of beings or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     financement
    0.36
     دہشت
    0.33
     ilç
    0.30
     éduc
    0.30
     financiación
    0.30
     umfass
    0.29
    成长
    0.29
    Liens
    0.29
     unlaw
    0.29
     düzey
    0.28
    POSITIVE LOGITS
     animal
    0.38
     deciduous
    0.32
     animals
    0.31
    動物
    0.30
     cows
    0.29
    ラ
    0.29
    veget
    0.28
    >
    0.28
     person
    0.27
    animal
    0.27
    Act Density 0.163%

    No Known Activations