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

    Neuronpedia

    INDEX
    Explanations

    g, compet, hoch, bi, dash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    2.12
    ب
    2.03
    и
    2.02
    തിരെ
    1.78
    ка
    1.78
    ma
    1.77
    ths
    1.75
    Eras
    1.67
    งาม
    1.64
    cie
    1.60
    POSITIVE LOGITS
     vamos
    2.22
     regard
    2.10
    𝗧
    2.10
     blames
    2.08
     "":
    2.07
     overlapping
    2.05
     '':
    2.04
     overlaps
    2.04
     oversaw
    2.02
    ר
    2.02
    Act Density 0.000%

    No Known Activations