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

    Neuronpedia

    INDEX
    Explanations

    negations or prefixes suggesting absence or the concept of "not."

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

    starting with "un"

    np_acts-logits-general · gemini-2.0-flash

    words starting with un

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Same
    -0.60
     anhänger
    -0.58
     bè
    -0.57
     Perla
    -0.53
     umgekehrt
    -0.51
     excursion
    -0.50
    同上
    -0.50
     cumplido
    -0.50
    štu
    -0.49
     erle
    -0.49
    POSITIVE LOGITS
     unt
    0.80
     un
    0.74
     تضيفلها
    0.70
     Unt
    0.69
     EGL
    0.68
     unre
    0.68
    Geplaatst
    0.68
     unf
    0.67
     ung
    0.63
    EGL
    0.62
    Act Density 0.105%

    No Known Activations