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

    Neuronpedia

    INDEX
    Explanations

    java and rust imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schreib
    0.49
     prá
    0.45
     chocolat
    0.43
     gráficos
    0.43
     propio
    0.42
     permesso
    0.42
     textbook
    0.42
    tgt
    0.42
     cargas
    0.41
     корпу
    0.40
    POSITIVE LOGITS
    urai
    0.48
    ail
    0.47
    其他
    0.47
    ace
    0.46
    otions
    0.45
    אַ
    0.45
    are
    0.44
    .’”
    0.44
    ”—
    0.44
     მაგრამ
    0.44
    Act Density 0.045%

    No Known Activations