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

    Neuronpedia

    INDEX
    Explanations

    following 'FROM' or listing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зала
    0.44
     세포
    0.38
     satir
    0.38
     allegory
    0.36
     निसाब
    0.35
     angios
    0.35
    无穷
    0.35
     histoire
    0.35
     poems
    0.35
     변화
    0.35
    POSITIVE LOGITS
    il
    0.36
    ď
    0.36
    remaining
    0.36
    nd
    0.34
    www
    0.34
     další
    0.33
    verters
    0.33
     outgoing
    0.32
    presentasikan
    0.32
    ol
    0.31
    Act Density 0.008%

    No Known Activations