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

    Neuronpedia

    INDEX
    Explanations

    colors or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.47
    it
    0.46
     greatly
    0.46
    mex
    0.46
    kj
    0.45
     Weg
    0.42
     Valent
    0.42
    rir
    0.42
     Dob
    0.42
     wed
    0.41
    POSITIVE LOGITS
    當年
    0.46
     సందర్భ
    0.44
     மற்றும்
    0.42
    ául
    0.42
    乃至
    0.42
    顏色
    0.42
     ⋮
    0.42
     또는
    0.41
    बाट
    0.41
    耑
    0.41
    Act Density 0.002%

    No Known Activations