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

    Neuronpedia

    INDEX
    Explanations

    engine, load, error, simpler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amalfi
    0.76
     HIM
    0.72
    ﻜ
    0.71
    פה
    0.70
     Kavanaugh
    0.70
     unfor
    0.70
     Asha
    0.69
     Hemingway
    0.68
     Puglia
    0.68
    ༨
    0.68
    POSITIVE LOGITS
    ose
    0.81
    듕
    0.77
     વિચાર
    0.76
    zonych
    0.73
    apd
    0.71
    比賽
    0.70
    emers
    0.69
    ost
    0.68
    ais
    0.66
    ots
    0.66
    Act Density 0.087%

    No Known Activations