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

    Neuronpedia

    INDEX
    Explanations

    Number 100

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the text refers to “opacity” settings or opacity values (e.g. the word “Opacity” and its numeric/percentage parameters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     circular
    -0.06
    ünün
    -0.06
    Safe
    -0.06
     مختلف
    -0.06
    Repository
    -0.06
    _increment
    -0.06
     suma
    -0.06
     Macro
    -0.06
    (pow
    -0.06
    .every
    -0.06
    POSITIVE LOGITS
     nik
    0.07
    eh
    0.06
     Presidents
    0.06
     Bew
    0.06
    qr
    0.06
     Barbar
    0.06
     canyon
    0.06
     😉↵↵
    0.06
     Rivers
    0.06
    ustria
    0.06
    Act Density 0.011%

    No Known Activations