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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gas
    -0.07
    _decoder
    -0.07
    _CO
    -0.07
    ILL
    -0.07
    ⇑
    -0.06
    classes
    -0.06
    融为一体
    -0.06
     �
    -0.06
    不足以
    -0.06
    /top
    -0.06
    POSITIVE LOGITS
    _series
    0.07
    .hours
    0.07
    реб
    0.07
     {!!
    0.07
    "...
    0.07
    俑
    0.06
    entered
    0.06
    mil
    0.06
    ]byte
    0.06
    <hr
    0.06
    Act Density 0.008%

    No Known Activations