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

    Neuronpedia

    INDEX
    Explanations

    references to cats

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

    cat, cat hairs, Cat Power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Springsteen
    -0.50
    Życiorys
    -0.50
     للاسماء
    -0.49
    });
    -0.49
    titleMargin
    -0.49
    )});
    -0.48
     estekak
    -0.47
    OGND
    -0.47
     ]
    -0.47
    ◆◇
    -0.47
    POSITIVE LOGITS
    Cat
    1.12
     Cat
    1.05
     cat
    1.05
    cat
    1.04
     cats
    0.93
     Cats
    0.89
    CAT
    0.87
    Cats
    0.86
     CAT
    0.83
    cats
    0.83
    Act Density 0.010%

    No Known Activations