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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron detects individual uppercase initials followed by a period in names (e.g., “R.”, “E.”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yes
    -0.07
     miners
    -0.07
     GitHub
    -0.07
    etzt
    -0.06
    gold
    -0.06
     mucho
    -0.06
     eos
    -0.06
     Void
    -0.06
    algorithm
    -0.06
    licenses
    -0.06
    POSITIVE LOGITS
     Northwestern
    0.07
     QU
    0.06
     fireworks
    0.06
     PI
    0.06
    .Measure
    0.06
     onPostExecute
    0.06
     WE
    0.06
     intensified
    0.06
    -distance
    0.06
    _are
    0.06
    Act Density 0.009%

    No Known Activations