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

    Neuronpedia

    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash

    The neuron detects decimal numeric values (floating‐point measurements or concentrations) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _drop
    -0.08
     dünyanın
    -0.08
    센터
    -0.07
    _dd
    -0.07
    Nếu
    -0.07
     multin
    -0.07
     railroad
    -0.07
     sistemi
    -0.07
     ---------
    -0.06
    uniq
    -0.06
    POSITIVE LOGITS
    _est
    0.07
    maid
    0.06
    .private
    0.06
    .person
    0.06
     zvlá
    0.06
    Inflater
    0.06
    ाहत
    0.05
    Privacy
    0.05
    ght
    0.05
    **(
    0.05
    Act Density 0.009%

    No Known Activations