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

    Neuronpedia

    INDEX
    Explanations

    fly, ward, bed, alk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.91
     is
    0.72
    et
    0.71
     on
    0.71
     at
    0.69
    AN
    0.68
    i
    0.64
     n
    0.62
    os
    0.59
     satisfe
    0.59
    POSITIVE LOGITS
    ने
    0.92
    ة
    0.78
    ской
    0.73
     ਇੱਕ
    0.73
    نے
    0.71
    ปี
    0.68
    ید
    0.68
    ช่วง
    0.66
    กัน
    0.64
    한
    0.64
    Act Density 0.056%

    No Known Activations