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

    Neuronpedia

    INDEX
    Explanations

    finances/auditing/calculations

    np_max-act · gemini-2.0-flash

    The neuron picks up and highlights non‐integer numeric tokens, i.e. floating‐point decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Vision
    -0.08
    _fw
    -0.07
     бу
    -0.07
    itizen
    -0.07
    NM
    -0.06
     dem
    -0.06
    Forward
    -0.06
    ठन
    -0.06
    frame
    -0.06
    Target
    -0.06
    POSITIVE LOGITS
    ，此
    0.06
    ита
    0.06
     Hydro
    0.06
     ","
    0.06
    �璃
    0.06
     nett
    0.06
    인
    0.06
    :'',
    0.06
     воспал
    0.06
    �다
    0.06
    Act Density 0.014%

    No Known Activations