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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    [counter
    -0.07
    "</
    -0.07
    .APP
    -0.07
    (DEFAULT
    -0.07
    如今
    -0.07
     agree
    -0.07
    Փ
    -0.06
    �
    -0.06
    bstract
    -0.06
     commented
    -0.06
    POSITIVE LOGITS
    gesture
    0.08
    IOC
    0.07
    -in
    0.07
    Bytes
    0.07
    艚
    0.07
    -way
    0.07
    رة
    0.07
     đỏ
    0.07
    \b
    0.07
     קורה
    0.07
    Act Density 0.079%

    No Known Activations