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

    Neuronpedia

    INDEX
    Explanations

    references to animals and wildlife

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

    animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lead
    -0.51
     concise
    -0.50
    gout
    -0.46
     Royce
    -0.45
     leads
    -0.45
     succinct
    -0.43
     Concise
    -0.43
    });
    -0.43
    %)$
    -0.42
    lead
    -0.42
    POSITIVE LOGITS
     Animals
    1.74
    Animals
    1.68
     animals
    1.68
    animals
    1.54
     ANIMALS
    1.51
    Animal
    1.48
     Animal
    1.45
     animal
    1.45
    animal
    1.42
     animais
    1.30
    Act Density 0.011%

    No Known Activations