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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    memberof
    -0.07
    _OPER
    -0.07
    _point
    -0.07
    러스
    -0.06
    notin
    -0.06
    	block
    -0.06
     Lowell
    -0.06
     Walker
    -0.06
     classe
    -0.06
     Oregon
    -0.06
    POSITIVE LOGITS
     zajímav
    0.07
     soğ
    0.07
    (input
    0.07
     yı
    0.07
     CType
    0.06
     Cute
    0.06
    _pipeline
    0.06
     režim
    0.06
     stern
    0.06
    ===============↵
    0.06
    Act Density 0.008%

    No Known Activations