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

    Neuronpedia

    INDEX
    Explanations

    chili con consecuencias

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.51
    ."
    0.45
    state
    0.45
    elling
    0.43
    amu
    0.43
    land
    0.43
     United
    0.42
    nd
    0.42
    api
    0.41
     According
    0.41
    POSITIVE LOGITS
     मोठा
    0.51
    خاص
    0.49
     puas
    0.48
     فأ
    0.47
     mais
    0.46
     приме
    0.46
    但他
    0.46
     αλλά
    0.45
     possibilité
    0.45
     حتی
    0.45
    Act Density 0.007%

    No Known Activations