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

    Neuronpedia

    INDEX
    Explanations

    .edu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    场地
    -0.08
    干扰
    -0.07
    阻挡
    -0.07
    긿
    -0.07
    ITU
    -0.07
    	raw
    -0.07
     PACK
    -0.06
     hepatitis
    -0.06
    UBY
    -0.06
    	bar
    -0.06
    POSITIVE LOGITS
     stove
    0.07
    女神
    0.07
    moon
    0.07
     Schwar
    0.07
    !?
    0.07
    ustomed
    0.07
     camper
    0.07
    ㉠
    0.06
     fiance
    0.06
    шим
    0.06
    Act Density 0.002%

    No Known Activations