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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    脑海
    -0.08
    	part
    -0.07
    <uint
    -0.07
     FAT
    -0.07
    .prom
    -0.07
     began
    -0.07
     BTN
    -0.07
    .hit
    -0.07
     Expedition
    -0.07
    跞
    -0.06
    POSITIVE LOGITS
    Ρ
    0.07
    om
    0.07
    农场
    0.07
    ordering
    0.07
    把
    0.07
    𝑋
    0.06
    pciones
    0.06
    看得
    0.06
    樣
    0.06
    品
    0.06
    Act Density 0.007%

    No Known Activations