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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron activates on Python traceback lines, i.e. file‐path and line‐number error messages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ��
    -0.06
    pell
    -0.06
     kendine
    -0.06
     Installed
    -0.06
     sends
    -0.06
    듯
    -0.06
    ені
    -0.06
    esine
    -0.06
    ển
    -0.05
    embre
    -0.05
    POSITIVE LOGITS
     batchSize
    0.07
    Northern
    0.07
    remark
    0.07
    صر
    0.07
    $view
    0.07
    East
    0.07
    /npm
    0.07
    editing
    0.06
    cdc
    0.06
     MOT
    0.06
    Act Density 0.001%

    No Known Activations