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

    Neuronpedia

    INDEX
    Explanations

    using System;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выз
    0.79
     получается
    0.74
     सोडा
    0.74
    dan
    0.69
     выполнения
    0.69
    ैग
    0.68
     utilizza
    0.68
    ़
    0.68
     zwią
    0.64
    िं
    0.64
    POSITIVE LOGITS
    AutoScaleMode
    0.82
     DBox
    0.73
    bibinfo
    0.72
    ला
    0.70
    zeitig
    0.70
    mathbf
    0.69
     worrying
    0.68
     eradic
    0.68
    чика
    0.67
     defying
    0.65
    Act Density 0.004%

    No Known Activations