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

    Neuronpedia

    INDEX
    Explanations

    releasing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    六
    -0.07
     distinctive
    -0.07
     theological
    -0.07
    ToDevice
    -0.06
     Иванов
    -0.06
    lations
    -0.06
     pastoral
    -0.06
    itious
    -0.06
    нів
    -0.06
    Formation
    -0.06
    POSITIVE LOGITS
    品牌
    0.08
     张
    0.07
    {},↵
    0.06
    [I
    0.06
    `),↵
    0.06
    [s
    0.06
    'h
    0.06
     �
    0.06
     skupiny
    0.06
    	C
    0.06
    Act Density 0.034%

    No Known Activations