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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.53
    Diversity
    0.53
    ت
    0.50
    M
    0.48
    ق
    0.48
    rev
    0.48
    to
    0.47
    It
    0.47
    C
    0.46
    N
    0.46
    POSITIVE LOGITS
     vraie
    0.51
     foodie
    0.47
     ट्रू
    0.47
     événement
    0.46
    粞
    0.46
     инду
    0.46
    ною
    0.45
     ጉ
    0.45
     folos
    0.45
     chimie
    0.45
    Act Density 0.001%

    No Known Activations