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

    Neuronpedia

    INDEX
    Explanations

    1-800-843-5678

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    巉
    0.51
    াদেশিক
    0.50
    zież
    0.50
    ಬ್ಬಿಣ
    0.50
    getRepository
    0.49
    비스
    0.49
     खाद
    0.49
    0.49
    翮
    0.49
    澼
    0.48
    POSITIVE LOGITS
    a
    0.67
    i
    0.62
    0.52
    r
    0.50
    p
    0.50
    円
    0.47
    c
    0.46
    an
    0.45
    e
    0.43
     ramos
    0.42
    Act Density 0.004%

    No Known Activations