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

    Neuronpedia

    INDEX
    Explanations

    seeing and observing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    и
    1.04
    canc
    0.93
    Asimismo
    0.91
    เสียง
    0.90
    সাধন
    0.89
    üğünüz
    0.88
     procede
    0.87
    পি
    0.86
     canciones
    0.86
     درس
    0.85
    POSITIVE LOGITS
     👀
    2.01
     xét
    1.77
    眈
    1.65
    tower
    1.63
     eye
    1.54
    👀
    1.49
     helplessly
    1.45
     acuity
    1.38
    HasStarred
    1.37
    দেখিতে
    1.34
    Act Density 0.448%

    No Known Activations