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

    Neuronpedia

    INDEX
    Explanations

    INDEX, HI, SIDE, spectral, color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    0.85
    an
    0.70
    t
    0.68
    you
    0.67
    ק
    0.64
    til
    0.63
    tis
    0.62
    till
    0.61
    tid
    0.59
    tet
    0.59
    POSITIVE LOGITS
    ের
    0.66
    માં
    0.66
     khi
    0.61
     ktoré
    0.60
     số
    0.59
    ри
    0.59
     často
    0.57
     dân
    0.57
     تي
    0.57
     quê
    0.54
    Act Density 0.000%

    No Known Activations