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

    Neuronpedia

    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by floating-point numbers (decimal numerals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     выз
    -0.07
    _PT
    -0.07
    _sequence
    -0.06
     Writer
    -0.06
    MULT
    -0.06
     Rage
    -0.06
     overhe
    -0.06
     mist
    -0.06
     худож
    -0.06
    xffffffff
    -0.06
    POSITIVE LOGITS
    cancel
    0.07
    +",
    0.07
    Datas
    0.07
     admission
    0.06
    reira
    0.06
     --}}↵
    0.06
     출시
    0.06
     вертик
    0.06
    -board
    0.06
     Farmers
    0.06
    Act Density 0.170%

    No Known Activations