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

    Neuronpedia

    INDEX
    Explanations

    introducing a topic

    np_max-act · gemini-2.0-flash

    The neuron never activates—it doesn’t detect any patterns in the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Canucks
    -0.06
    409
    -0.06
     QQ
    -0.06
     Titans
    -0.06
    android
    -0.06
    gram
    -0.06
    ancybox
    -0.06
    ัคร
    -0.05
    207
    -0.05
    washer
    -0.05
    POSITIVE LOGITS
    .Metro
    0.07
    ();"
    0.07
    ."</
    0.07
     ambiguous
    0.07
     PrintWriter
    0.07
    *)"
    0.07
     [`
    0.06
     "}
    0.06
     목소
    0.06
    .remove
    0.06
    Act Density 0.119%

    No Known Activations