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

    Neuronpedia

    INDEX
    Explanations

    elements related to crafting or decoration

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

    Exclamations and truncated sentences followed by "I"

    np_acts-logits-general · gemini-2.0-flash

    dots and german words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.96
     shitty
    -0.95
    klart
    -0.91
     tbh
    -0.90
     fucking
    -0.90
     fucks
    -0.87
     FUCKING
    -0.86
     goddamn
    -0.86
    Geplaatst
    -0.86
     ͡°
    -0.85
    POSITIVE LOGITS
     muß
    0.78
     müßte
    0.73
     mußte
    0.66
     läßt
    0.66
    ................
    0.62
    ...............
    0.59
    ........
    0.59
    ・・・・・
    0.59
    .........
    0.58
    ・・・・
    0.56
    Act Density 0.289%

    No Known Activations