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

    Neuronpedia

    INDEX
    Explanations

    Antonio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    归属于
    -0.07
    🔟
    -0.07
     relat
    -0.07
     khỏi
    -0.07
    쉐
    -0.06
    stime
    -0.06
    طار
    -0.06
    谳
    -0.06
    صحاب
    -0.06
    出生于
    -0.06
    POSITIVE LOGITS
    rites
    0.07
    \">↵
    0.07
    _DETAIL
    0.07
     dramas
    0.07
     barrier
    0.07
     manip
    0.07
     REPL
    0.07
     facets
    0.07
    irts
    0.06
     Currency
    0.06
    Act Density 0.001%

    No Known Activations