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

    Neuronpedia

    INDEX
    Explanations

    references to different forms and qualities of water

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

    water followed by related entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ggior
    -0.56
     idéia
    -0.54
     mijne
    -0.53
    __(/*!
    -0.52
     gius
    -0.52
     AssemblyCompany
    -0.52
     coroa
    -0.50
     soste
    -0.50
    slug
    -0.49
    diga
    -0.48
    POSITIVE LOGITS
    Water
    1.23
     Water
    1.21
     water
    1.16
     WATER
    1.08
    water
    1.00
    WATER
    0.94
     Wasser
    0.94
    Wasser
    0.93
    Waters
    0.91
     Waters
    0.90
    Act Density 0.022%

    No Known Activations