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

    Neuronpedia

    INDEX
    Explanations

    implicit expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dwie
    0.76
    Pl
    0.67
    佳
    0.66
    优秀的
    0.65
    Syn
    0.65
    優秀
    0.64
    찌
    0.63
     Versch
    0.63
    孩
    0.63
    ިޔ
    0.63
    POSITIVE LOGITS
     slump
    0.86
     slouch
    0.75
    कृत
    0.74
     Hold
    0.72
     carelessness
    0.70
     life
    0.70
     drawing
    0.68
     wings
    0.68
    បើ
    0.68
     dred
    0.67
    Act Density 0.000%

    No Known Activations