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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (setq
    -0.07
    IpAddress
    -0.06
    .zone
    -0.06
     polluted
    -0.06
     Newtonsoft
    -0.06
     متخصص
    -0.06
     Iraq
    -0.06
    rech
    -0.06
     skirt
    -0.06
    -sided
    -0.06
    POSITIVE LOGITS
     +↵↵
    0.07
    도록
    0.07
    exemple
    0.07
     muchas
    0.07
     SERVER
    0.06
    ="__
    0.06
     асп
    0.06
    ¡
    0.06
    μιουργ
    0.06
     gü
    0.06
    Act Density 0.013%

    No Known Activations