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
    ultimo
    -0.07
    *N
    -0.07
    MatrixXd
    -0.07
    :black
    -0.07
    (operator
    -0.06
     موبایل
    -0.06
    Severity
    -0.06
    	fclose
    -0.06
    -degree
    -0.06
    serv
    -0.06
    POSITIVE LOGITS
     iht
    0.07
     SNMP
    0.06
     innovative
    0.06
     cih
    0.06
     DI
    0.06
    参考
    0.06
    rst
    0.06
    hall
    0.06
     rẻ
    0.06
     fuss
    0.06
    Act Density 0.002%

    No Known Activations