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

    Neuronpedia

    INDEX
    Explanations

    entities

    np_max-act · gemini-2.0-flash

    The neuron is primarily activated by the word “company” (and its possessive form “company’s”), i.e. occurrences referring to the company.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cooper
    -0.06
    auf
    -0.06
     NA
    -0.06
    ogeneous
    -0.06
    athlon
    -0.06
     eliminated
    -0.06
     plotting
    -0.06
     лист
    -0.06
     newArray
    -0.06
    omore
    -0.06
    POSITIVE LOGITS
    864
    0.07
     тверд
    0.07
    (bool
    0.07
     maxx
    0.07
    -val
    0.07
    _MAX
    0.06
    .__
    0.06
     utrecht
    0.06
    _TXT
    0.06
    _BOOLEAN
    0.06
    Act Density 0.090%

    No Known Activations