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

    Neuronpedia

    INDEX
    Explanations

    words related to medical procedures, solutions, and biology

    oai_token-act-pair · gemini-2.0-flash

    scientific solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.57
     chasse
    -0.51
     propOrder
    -0.50
    CodeAttribute
    -0.49
    oł
    -0.48
    غول
    -0.48
    ిక
    -0.47
     amnesty
    -0.47
    peteer
    -0.46
     forgiven
    -0.46
    POSITIVE LOGITS
     water
    0.66
    ValueGeneration
    0.59
    InitVars
    0.59
     intravenous
    0.58
     fresh
    0.56
     freshwater
    0.55
     bottles
    0.55
     beverage
    0.55
    :✨
    0.54
    Lähteet
    0.53
    Act Density 1.520%

    No Known Activations