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

    Neuronpedia

    INDEX
    Explanations

    Quotation/Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stan
    -0.07
     王
    -0.07
    iyan
    -0.07
    rending
    -0.06
    -vous
    -0.06
    μπο
    -0.06
    =id
    -0.06
    	Return
    -0.06
     seven
    -0.06
     เ�
    -0.06
    POSITIVE LOGITS
     waypoint
    0.07
    态
    0.07
    (commit
    0.06
    Identity
    0.06
    esModule
    0.06
    τωση
    0.06
    OUNTRY
    0.06
     діяльність
    0.06
    шла
    0.06
     بیرون
    0.05
    Act Density 0.015%

    No Known Activations