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

    Neuronpedia

    INDEX
    Explanations

    references to dogs and associated activities or characteristics

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

    dogs

    np_acts-logits-general · gemini-2.0-flash

    dogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anovich
    -0.70
     merid
    -0.64
     Rial
    -0.60
     Transparency
    -0.60
     Webber
    -0.60
     pinn
    -0.59
    vij
    -0.59
     Sust
    -0.59
     Arcadia
    -0.59
     Eel
    -0.58
    POSITIVE LOGITS
     dogs
    1.55
     dog
    1.43
     Dog
    1.37
     Dogs
    1.34
     DOG
    1.29
    Dogs
    1.27
    Dog
    1.26
     DOGS
    1.21
    dogs
    1.17
    DOG
    1.12
    Act Density 0.114%

    No Known Activations