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

    Neuronpedia

    INDEX
    Explanations

    audience interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.72
    :
    0.68
     fraîche
    0.67
    Ин
    0.66
     encara
    0.66
    િ
    0.66
    ┍
    0.66
     zove
    0.64
    ╔
    0.63
    ig
    0.63
    POSITIVE LOGITS
     móviles
    0.87
    誐
    0.86
    ối
    0.82
     olması
    0.80
    मिशन
    0.80
    lnk
    0.79
     conocimientos
    0.78
    renden
    0.78
    रियल
    0.77
    俥
    0.77
    Act Density 0.004%

    No Known Activations