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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SSE
    -0.06
    _past
    -0.06
    (ep
    -0.06
    ,right
    -0.06
    hover
    -0.06
    そこ
    -0.06
     نمونه
    -0.06
    ované
    -0.06
     보
    -0.06
     Dashboard
    -0.06
    POSITIVE LOGITS
    olics
    0.07
    :");↵↵
    0.07
     Granted
    0.07
     spirits
    0.06
     railroad
    0.06
    '});↵
    0.06
     knocks
    0.06
     PSI
    0.06
     reviewers
    0.06
     sigma
    0.06
    Act Density 0.042%

    No Known Activations