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

    Neuronpedia

    INDEX
    Explanations

    today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    па
    0.83
     congregate
    0.82
    ور
    0.82
     dryers
    0.80
    ों
    0.79
    すみ
    0.79
     verts
    0.78
    0.78
     reinstall
    0.77
    ਹੀ
    0.76
    POSITIVE LOGITS
    ள்ள
    0.89
    ﻕ
    0.88
    tien
    0.87
     پھر
    0.86
    ંત
    0.86
    l
    0.84
    eur
    0.79
    ীবন
    0.79
     puesta
    0.77
    이야
    0.77
    Act Density 0.262%

    No Known Activations