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

    Neuronpedia

    INDEX
    Explanations

    instances of formal directives or requirements

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

    Please, Mitochond, Episode, No, Tre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.41
    ########.
    -0.41
     pleaſure
    -0.38
     autorización
    -0.37
    ArgsConstructor
    -0.36
     Downvote
    -0.35
     hinh
    -0.35
     MenuView
    -0.34
    RTLD
    -0.34
    ſelf
    -0.34
    POSITIVE LOGITS
     blah
    0.69
    blah
    0.68
    Lorem
    0.67
    Blah
    0.60
    bla
    0.56
    ...')
    0.56
    lorem
    0.49
    ...</
    0.49
    })`
    0.49
     description
    0.49
    Act Density 0.019%

    No Known Activations