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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    the neuron detects the substring “/or” (as in “and/or”), i.e. occurrences of “/or” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _cover
    -0.08
    /screens
    -0.08
     Rent
    -0.07
     Clay
    -0.07
    .addCell
    -0.07
    .Broadcast
    -0.07
    (M
    -0.07
     дані
    -0.07
    .med
    -0.07
    _Config
    -0.06
    POSITIVE LOGITS
     parachute
    0.07
    roud
    0.06
    &);↵↵
    0.06
     потріб
    0.06
     ".↵
    0.05
    "))))↵
    0.05
    olid
    0.05
     rồi
    0.05
    342
    0.05
     Fah
    0.05
    Act Density 0.001%

    No Known Activations