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

    Neuronpedia

    INDEX
    Explanations

    users and tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erna
    0.76
    zić
    0.73
    靖
    0.68
    tr
    0.66
    しまう
    0.65
    eta
    0.65
     nice
    0.65
    にする
    0.64
     vỏ
    0.63
    、《
    0.62
    POSITIVE LOGITS
    ubjects
    1.49
    hp
    1.29
    hip
    1.29
    pecific
    1.25
    ofinstagram
    1.24
    htp
    1.23
    ociety
    1.21
    hips
    1.18
    pective
    1.14
    paces
    1.12
    Act Density 0.220%

    No Known Activations