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

    Neuronpedia

    INDEX
    Explanations

    references to structures or objects located beneath or under something

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

    a position below something

    np_acts-logits-general · gemini-2.0-flash

    spatial position below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.65
    :✨
    -0.57
    RegressionTest
    -0.54
    RenderAtEndOf
    -0.53
     Réponses
    -0.53
    Chham
    -0.53
    Personensuche
    -0.51
    انيف
    -0.49
     kasarigan
    -0.48
     الحره
    -0.48
    POSITIVE LOGITS
    neath
    0.68
     beneath
    0.60
    Beneath
    0.59
    setAccessible
    0.59
     Beneath
    0.58
    threshold
    0.55
     threshold
    0.55
    iculous
    0.55
     debajo
    0.53
     gång
    0.52
    Act Density 0.081%

    No Known Activations