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

    Neuronpedia

    INDEX
    Explanations

    references to water and hydration

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

    water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.49
     Rump
    -0.46
    iliation
    -0.44
    Portail
    -0.43
     socio
    -0.41
    zweig
    -0.41
    rump
    -0.40
    nagel
    -0.40
    henden
    -0.40
    tagPool
    -0.40
    POSITIVE LOGITS
     water
    0.76
     thirsty
    0.72
     agua
    0.66
     thirst
    0.65
     hydration
    0.64
     drinkers
    0.64
     WATER
    0.63
     drinking
    0.63
     água
    0.62
    Water
    0.62
    Act Density 0.010%

    No Known Activations