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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of water supply and sanitation (e.g., “water,” “safe water,” “sanitation”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Serum
    -0.07
     VIEW
    -0.07
    STAT
    -0.07
    сте
    -0.07
    С
    -0.07
     naughty
    -0.06
     roles
    -0.06
     Coverage
    -0.06
     KBS
    -0.06
    .Table
    -0.06
    POSITIVE LOGITS
    	category
    0.07
     sağlıklı
    0.06
     borderWidth
    0.06
    (dynamic
    0.06
    (::
    0.06
    _CHANGE
    0.06
     диаг
    0.06
    RouterModule
    0.06
     soğuk
    0.06
     увели
    0.06
    Act Density 0.006%

    No Known Activations