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 flags mentions of specific measured quantities—numbers paired with units or amounts (e.g. “1 tbsp,” “8 oz,” “water”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -With
    -0.07
     περί
    -0.06
    ailed
    -0.06
    ธาน
    -0.06
    ampp
    -0.06
    UTILITY
    -0.06
    Reality
    -0.06
    _GE
    -0.06
     Closet
    -0.06
    GetString
    -0.06
    POSITIVE LOGITS
    	initial
    0.08
     pok
    0.07
     emple
    0.07
     preparing
    0.07
     irc
    0.07
    ">(
    0.07
     supremacy
    0.06
    ’av
    0.06
     argv
    0.06
    ьют
    0.06
    Act Density 0.004%

    No Known Activations