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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions in the text

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

    "Still" or similar meaning (temporal adverb)

    np_acts-logits-general · gemini-2.0-flash

    still, yet, ongoing states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PyLong
    -0.53
    └──
    -0.52
    Autoritní
    -0.50
     onSuccess
    -0.50
    ιος
    -0.49
    esgue
    -0.48
    inaldi
    -0.48
     Leu
    -0.48
    իվ
    -0.47
     neoliber
    -0.47
    POSITIVE LOGITS
     هنوز
    1.18
    まだ
    1.16
     still
    1.16
    まだまだ
    1.14
    still
    1.12
     todavía
    1.10
    はまだ
    1.10
     until
    1.09
     Until
    1.03
    Still
    1.01
    Act Density 0.428%

    No Known Activations