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

    Neuronpedia

    INDEX
    Explanations

    Automatic Curriculum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ຄ
    0.42
     tinge
    0.41
    cerr
    0.39
     שלי
    0.39
    CHARLES
    0.39
     зміни
    0.39
     malfunctioning
    0.39
     सिक्
    0.38
     जागरण
    0.38
     cringe
    0.38
    POSITIVE LOGITS
    éth
    0.43
     በሽታ
    0.41
     обще
    0.40
    дә
    0.40
    ag
    0.40
     social
    0.40
     availability
    0.40
     စ
    0.40
    ୀ
    0.39
     agents
    0.39
    Act Density 0.009%

    No Known Activations