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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sen
    -0.07
     soát
    -0.07
     tekn
    -0.07
    借此
    -0.07
    secured
    -0.07
     Sensors
    -0.07
    รวย
    -0.07
     trainable
    -0.07
     mieux
    -0.07
    新たな
    -0.07
    POSITIVE LOGITS
    的经历
    0.07
    	The
    0.07
     INIT
    0.07
    .Statement
    0.07
    concept
    0.07
    ,this
    0.07
    缘
    0.06
    .Kind
    0.06
    (Input
    0.06
    感叹
    0.06
    Act Density 0.117%

    No Known Activations