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

    Neuronpedia

    INDEX
    Explanations

    choices

    np_max-act · gemini-2.0-flash

    The neuron activates on words that express selecting or configuring options (e.g., “choose,” “pick,” “design,” “want”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _smooth
    -0.07
    erer
    -0.06
    FromArray
    -0.06
    _Position
    -0.06
     |_|
    -0.06
    Collapse
    -0.06
    amics
    -0.06
    _multiplier
    -0.06
     spins
    -0.06
     thành
    -0.06
    POSITIVE LOGITS
    ();)
    0.08
    ">--}}↵
    0.07
     záb
    0.06
    щается
    0.06
    ENCE
    0.06
     EVENT
    0.06
     выб
    0.06
     Trans
    0.06
     істор
    0.06
     Arr
    0.06
    Act Density 0.049%

    No Known Activations