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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sn
    -0.07
    .eulerAngles
    -0.07
     身
    -0.07
    uctive
    -0.06
    .setContent
    -0.06
    frm
    -0.06
    _CR
    -0.06
     smooth
    -0.06
    vvm
    -0.06
     allem
    -0.06
    POSITIVE LOGITS
     terrorists
    0.08
     створення
    0.07
     Workspace
    0.06
    諾
    0.06
    Recipient
    0.06
     Contributor
    0.06
     procure
    0.06
    fifo
    0.06
     //
    0.06
     envoy
    0.06
    Act Density 0.019%

    No Known Activations