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

    Neuronpedia

    INDEX
    Explanations

    economic feasibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ം
    1.83
    ﻉ
    1.81
    larda
    1.73
     dejado
    1.70
    OLYBDENUM
    1.69
    부터
    1.68
     הח
    1.68
     קר
    1.63
     הש
    1.63
    い
    1.63
    POSITIVE LOGITS
    ors
    2.06
    offic
    1.93
    al
    1.91
    ния
    1.91
    ut
    1.88
    it
    1.88
    oil
    1.87
    szer
    1.87
    robot
    1.86
    orn
    1.85
    Act Density 0.013%

    No Known Activations