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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    当即
    -0.07
     cor
    -0.07
    本书
    -0.07
    机组
    -0.07
     Upon
    -0.07
    _upd
    -0.06
    (b
    -0.06
    ∂
    -0.06
    PRESENT
    -0.06
     evidence
    -0.06
    POSITIVE LOGITS
    䏡
    0.08
    .bb
    0.07
    Boy
    0.07
    .js
    0.07
    .setVertical
    0.07
    <bits
    0.07
    setMax
    0.07
    .recipe
    0.07
    _seek
    0.07
    �s
    0.07
    Act Density 0.013%

    No Known Activations