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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    propertyName
    -0.06
     즉
    -0.06
    ัด
    -0.06
    ализации
    -0.06
     damaging
    -0.06
    leneck
    -0.06
     бер
    -0.06
    razy
    -0.06
    omic
    -0.06
    асти
    -0.06
    POSITIVE LOGITS
     reference
    0.09
    itelné
    0.07
    pw
    0.07
     anak
    0.07
    흥
    0.07
    .fil
    0.07
    -----------
↵
    0.07
     의
    0.06
    										↵
    0.06
    (scanner
    0.06
    Act Density 0.003%

    No Known Activations