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

    Neuronpedia

    INDEX
    Explanations

    .css, .h, .hpp, .js

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Helper
    0.45
     kort
    0.42
     helix
    0.39
     Knowledge
    0.39
    Knowledge
    0.38
     érz
    0.38
     chạm
    0.38
     getValue
    0.38
     كنا
    0.38
    جل
    0.37
    POSITIVE LOGITS
     travailleurs
    0.41
     下さい
    0.41
    поль
    0.40
    ttes
    0.40
     "?
    0.39
    urous
    0.39
     һәм
    0.39
    alignat
    0.38
    cemment
    0.38
     সেজন্য
    0.38
    Act Density 0.004%

    No Known Activations