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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating testimony and statements made during court or legal proceedings

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

    Following discourse or dialogue

    np_acts-logits-general · gemini-2.0-flash

    German words and English uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.79
     cref
    -0.77
    klart
    -0.72
    ustainable
    -0.72
    sourced
    -0.68
     incentiv
    -0.66
    interopRequire
    -0.64
    uxta
    -0.64
     sourced
    -0.64
    REGEX
    -0.64
    POSITIVE LOGITS
     daß
    0.70
    luß
    0.67
     muß
    0.66
     müßte
    0.65
     biß
    0.62
    faßt
    0.58
     wuß
    0.57
     mußte
    0.57
     anybody
    0.57
    Anybody
    0.54
    Act Density 0.421%

    No Known Activations