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

    Neuronpedia

    INDEX
    Explanations

    references to horses or equine-related topics

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

    horses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Glanz
    -0.54
     Vista
    -0.54
     Teal
    -0.53
     Plenum
    -0.51
     Segura
    -0.51
    Obvious
    -0.50
    [{{
    -0.50
     Thru
    -0.50
     kasarigan
    -0.48
     Peek
    -0.47
    POSITIVE LOGITS
     horses
    1.88
     Horses
    1.72
     horse
    1.65
    horses
    1.58
    horse
    1.56
    Horses
    1.55
     Horse
    1.50
    Horse
    1.47
     HORSE
    1.41
     caballos
    1.34
    Act Density 0.002%

    No Known Activations