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

    Neuronpedia

    INDEX
    Explanations

    including or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scraper
    0.45
     unanimous
    0.41
     például
    0.40
     downg
    0.39
     downgraded
    0.39
     hombre
    0.38
     scheduler
    0.38
     دختر
    0.38
     weakly
    0.38
     harder
    0.38
    POSITIVE LOGITS
    行李
    0.40
    লায়
    0.38
    驪
    0.38
    Roses
    0.38
    硃
    0.37
    ellery
    0.37
     Alo
    0.37
     theres
    0.37
    connectivity
    0.37
    busters
    0.36
    Act Density 0.000%

    No Known Activations