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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pn
    -0.07
     Ví
    -0.07
     refactor
    -0.06
    wiąz
    -0.06
    uco
    -0.06
    aphael
    -0.06
    اوه
    -0.06
    우스
    -0.06
    ød
    -0.06
    'яз
    -0.06
    POSITIVE LOGITS
    .parsers
    0.07
    (PDO
    0.06
     tooltips
    0.06
    -cert
    0.06
     consenting
    0.06
    	assertThat
    0.06
     thrilled
    0.06
     politely
    0.06
     repreh
    0.06
     toDate
    0.06
    Act Density 0.009%

    No Known Activations