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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “type” (as in “of the type …”) in technical or formal descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ути
    -0.07
    -worker
    -0.06
     оконч
    -0.06
     bite
    -0.06
    :inline
    -0.06
     deepcopy
    -0.06
     Cyber
    -0.06
     事
    -0.06
    처
    -0.06
     stabbing
    -0.06
    POSITIVE LOGITS
    _DIRECTION
    0.07
     فور
    0.06
     *.
    0.06
     msec
    0.06
    hort
    0.06
     tipo
    0.06
     "*
    0.06
     şimdi
    0.06
     (*.
    0.06
     BTN
    0.06
    Act Density 0.009%

    No Known Activations