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

    Neuronpedia

    INDEX
    Explanations

    deletion errors

    np_max-act · gemini-2.0-flash

    mentions of medical accidents, errors, or patient-harm incidents (surgical mistakes, overdoses, or injuries) in clinical or hospital contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     kayn
    -0.07
    転
    -0.07
     execut
    -0.07
     $\
    -0.06
     echang
    -0.06
     швид
    -0.06
     چون
    -0.06
     moll
    -0.06
    Lint
    -0.06
    、この
    -0.06
    POSITIVE LOGITS
    |"
    0.07
     BTC
    0.07
     hel
    0.07
     attacker
    0.06
    -U
    0.06
    _MORE
    0.06
     Paragraph
    0.06
    testing
    0.06
    ier
    0.06
    登録
    0.06
    Act Density 0.331%

    No Known Activations