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

    Neuronpedia

    INDEX
    Explanations

    geocode path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.44
    Physics
    0.43
    为什么
    0.43
    ও
    0.43
    Probability
    0.42
    Understand
    0.42
    It
    0.41
    That
    0.41
    I
    0.41
    Google
    0.41
    POSITIVE LOGITS
     pâ
    0.46
     enfants
    0.45
     vivre
    0.40
     picnic
    0.39
     ér
    0.39
     partai
    0.39
     ombre
    0.39
     usk
    0.38
     già
    0.38
     pä
    0.38
    Act Density 0.015%

    No Known Activations