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

    Neuronpedia

    INDEX
    Explanations

    I can speak Chinese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಈ
    0.50
    𝐬
    0.44
    િસ
    0.43
    𝙨
    0.42
    ק
    0.41
    的な
    0.41
    observations
    0.41
    definite
    0.41
     услы
    0.40
    chsel
    0.40
    POSITIVE LOGITS
     dresses
    0.44
     Dresses
    0.44
     dressed
    0.42
     perbedaan
    0.41
     mesin
    0.40
     issue
    0.40
     unas
    0.39
     completion
    0.39
     between
    0.39
     coerced
    0.38
    Act Density 0.002%

    No Known Activations