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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (DIR
    -0.08
     '..',
    -0.07
    imulator
    -0.07
    igate
    -0.07
    一颗
    -0.07
    劈
    -0.07
    进行全面
    -0.07
     czy
    -0.07
    浮现
    -0.07
     nằm
    -0.06
    POSITIVE LOGITS
    ὧ
    0.07
     nozzle
    0.07
     Rectangle
    0.07
     Oakland
    0.07
     compact
    0.06
    horizontal
    0.06
    設定
    0.06
    BP
    0.06
     Social
    0.06
    bau
    0.06
    Act Density 0.000%

    No Known Activations