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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	display
    -0.07
     hysteria
    -0.07
     deser
    -0.06
    시간
    -0.06
     key
    -0.06
    amilies
    -0.06
    pu
    -0.06
    nostic
    -0.06
    Overflow
    -0.06
     Historic
    -0.06
    POSITIVE LOGITS
    abilecek
    0.07
     continent
    0.06
    ProducesResponseType
    0.06
     появи
    0.06
     besten
    0.06
    avec
    0.06
    都会
    0.06
     propagated
    0.06
    [column
    0.06
     adding
    0.06
    Act Density 0.003%

    No Known Activations