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

    Neuronpedia

    INDEX
    Explanations

    Latin placeholder text

    np_max-act · gemini-2.0-flash

    This neuron activates on Latin‐looking placeholder (“Lorem Ipsum”) text fragments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Movies
    -0.09
     twitter
    -0.07
    ,out
    -0.07
     collector
    -0.07
     dạy
    -0.07
     وز
    -0.06
    popup
    -0.06
    [V
    -0.06
    (Button
    -0.06
    eza
    -0.06
    POSITIVE LOGITS
     quelques
    0.07
     Так
    0.06
     zprac
    0.06
    -toolbar
    0.06
    наслід
    0.06
    lickr
    0.06
    _um
    0.06
    �
    0.06
    快速
    0.06
     bluetooth
    0.06
    Act Density 0.002%

    No Known Activations