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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hear
    -0.07
     return
    -0.07
    coords
    -0.07
    -corner
    -0.07
     Expense
    -0.07
     it
    -0.07
    Persons
    -0.07
    (cookie
    -0.06
     confirmation
    -0.06
     denies
    -0.06
    POSITIVE LOGITS
    Jak
    0.06
    џџџџџџџџ
    0.06
    (^
    0.06
    _ylim
    0.06
    orů
    0.06
     дозволя
    0.06
    ,LOCATION
    0.06
     popis
    0.06
    ेदन
    0.06
    ozici
    0.06
    Act Density 0.015%

    No Known Activations