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

    Neuronpedia

    INDEX
    Explanations

    discouraging or ridiculing remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이해
    0.48
     querer
    0.47
     invitados
    0.46
    стым
    0.46
    ﻚ
    0.45
     жидкости
    0.44
    उ
    0.44
    стый
    0.44
    saint
    0.43
    澪
    0.43
    POSITIVE LOGITS
    ken
    0.43
    er
    0.43
    allelujah
    0.42
    all
    0.40
     wrong
    0.39
     Trends
    0.38
    math
    0.38
     (
    0.38
     sensing
    0.38
    w
    0.37
    Act Density 0.000%

    No Known Activations