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

    Neuronpedia

    INDEX
    Explanations

    data extraction/status labeling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ryo
    -0.07
    תכנ
    -0.07
     Training
    -0.07
     shoppers
    -0.07
     Starts
    -0.07
    ᴙ
    -0.06
     ;;^
    -0.06
    議
    -0.06
     Veterinary
    -0.06
    殁
    -0.06
    POSITIVE LOGITS
    .crt
    0.09
    张某
    0.08
    始终
    0.08
     salt
    0.07
     cgi
    0.07
    伤心
    0.07
    还可
    0.07
     FILTER
    0.07
    就在于
    0.07
     Bold
    0.07
    Act Density 0.002%

    No Known Activations