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

    Neuronpedia

    INDEX
    Explanations

    common stop words/punctuation

    np_max-act · gemini-2.0-flash

    The neuron never activates on any token—it appears to be a “dead” neuron that doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rulers
    -0.07
    creature
    -0.07
    负责
    -0.06
    avorites
    -0.06
    needed
    -0.06
    wares
    -0.06
     Lehr
    -0.06
     brains
    -0.06
     BPM
    -0.06
    utilus
    -0.06
    POSITIVE LOGITS
    .reduce
    0.07
     chasing
    0.07
    _Invoke
    0.07
     argparse
    0.06
     над
    0.06
     inner
    0.06
    ![
    0.06
     *);↵↵
    0.06
     pel
    0.06
     روسی
    0.06
    Act Density 0.000%

    No Known Activations