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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egis
    -0.07
    PASS
    -0.07
     thừa
    -0.06
     dismantle
    -0.06
     endorse
    -0.06
    ipe
    -0.06
    Friday
    -0.06
     READ
    -0.06
     nghị
    -0.06
    testimonial
    -0.06
    POSITIVE LOGITS
    )*/↵
    0.07
    /")↵
    0.06
    [temp
    0.06
    	Http
    0.06
    าคาร
    0.06
    错
    0.06
     */}↵
    0.06
     Yii
    0.06
    thr
    0.06
     ">"
    0.06
    Act Density 0.005%

    No Known Activations