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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects common “___ of” quantifier phrases (e.g. “Much of,” “Most of,” “Many of”) that introduce a large-portion statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     datingsider
    -0.07
    harga
    -0.07
     counters
    -0.07
    	error
    -0.07
    acılık
    -0.07
    ilians
    -0.06
    -driver
    -0.06
     lineman
    -0.06
    tabla
    -0.06
    iland
    -0.06
    POSITIVE LOGITS
    /ext
    0.07
    _ICON
    0.06
     ushort
    0.06
     Fuel
    0.06
    Slf
    0.06
     Sent
    0.06
     Swing
    0.06
     Biological
    0.06
    另一
    0.06
    }:{
    0.06
    Act Density 0.030%

    No Known Activations