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

    Neuronpedia

    INDEX
    Explanations

    descriptions of things that rise or fly

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

    height, flight, soaring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.51
    夕
    -0.48
    updateData
    -0.48
     avis
    -0.48
     bench
    -0.47
    estacks
    -0.47
     indis
    -0.47
    ubehör
    -0.46
    DBMS
    -0.46
    inois
    -0.46
    POSITIVE LOGITS
     soaring
    1.57
     soar
    1.47
     soared
    1.34
     volando
    0.69
     flying
    0.64
     towering
    0.61
     lofty
    0.60
    Flying
    0.60
     vuelos
    0.60
     Flying
    0.59
    Act Density 0.003%

    No Known Activations