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

    Neuronpedia

    INDEX
    Explanations

    references to water and its properties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.60
    tvguidetime
    -0.52
     EconPapers
    -0.43
    ailangan
    -0.43
    digm
    -0.42
    LookAnd
    -0.42
    RegistryLite
    -0.41
     cruzar
    -0.41
     abordagem
    -0.41
     myö
    -0.41
    POSITIVE LOGITS
     water
    0.81
     Water
    0.76
    Water
    0.67
    water
    0.60
     WATER
    0.60
     woda
    0.55
     Вода
    0.54
     вода
    0.52
     voda
    0.50
     vatten
    0.50
    Act Density 0.027%

    No Known Activations