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

    Neuronpedia

    INDEX
    Explanations

    film thickness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRD
    0.45
    INCREMENT
    0.42
     intestate
    0.40
    istrano
    0.39
    /<%=
    0.38
    条款
    0.37
    験
    0.37
     NSLog
    0.37
    DefineConstants
    0.37
    میٹ
    0.37
    POSITIVE LOGITS
    ێن
    0.41
    তাহাদের
    0.41
     Lek
    0.40
     रहस्य
    0.39
    akes
    0.39
    ेंद
    0.39
     circle
    0.38
    }$=
    0.38
     power
    0.38
     crusade
    0.37
    Act Density 0.010%

    No Known Activations