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

    Neuronpedia

    INDEX
    Explanations

    Encyclopedia Britannica

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.80
    S
    0.75
    J
    0.74
    '
    0.71
    0.70
    F
    0.69
    f
    0.68
    V
    0.66
    Y
    0.66
    N
    0.66
    POSITIVE LOGITS
     Britannica
    0.65
    <unused2135>
    0.57
    蚪
    0.56
    䊀
    0.55
     ಸಂಧಿ
    0.54
     ailments
    0.54
    Hitpoint
    0.53
    ),”
    0.52
     Aucun
    0.52
    йович
    0.52
    Act Density 0.003%

    No Known Activations