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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on evaluative or hedging words and degree modifiers (e.g. fairly, still, many, doesn’t, somehow) that qualify statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    راف
    -0.06
    �
    -0.06
    QWidget
    -0.06
    odafone
    -0.06
    _us
    -0.06
     перек
    -0.05
    到
    -0.05
    ION
    -0.05
     Adoles
    -0.05
     překvap
    -0.05
    POSITIVE LOGITS
     présent
    0.07
     Shir
    0.07
    owych
    0.07
    (messages
    0.07
    .Errorf
    0.07
    .AddWithValue
    0.07
     utmost
    0.07
    	char
    0.07
     NSS
    0.07
     exposures
    0.07
    Act Density 0.089%

    No Known Activations