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

    Neuronpedia

    INDEX
    Explanations

    Stories

    np_max-act · gemini-2.0-flash

    The neuron activates on character references—proper names and personal pronouns (I, he, she, Name_1, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     řízení
    -0.07
    xn
    -0.07
    _commands
    -0.07
    (ab
    -0.07
     alleen
    -0.07
     Horizontal
    -0.07
    rike
    -0.06
     machen
    -0.06
     única
    -0.06
    арод
    -0.06
    POSITIVE LOGITS
    $fdata
    0.07
    /response
    0.07
    pollo
    0.06
     disagrees
    0.06
     NSNumber
    0.06
     GLUT
    0.06
     enctype
    0.06
    \Helpers
    0.06
    .Net
    0.06
    unlikely
    0.06
    Act Density 0.023%

    No Known Activations