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

    Neuronpedia

    INDEX
    Explanations

    indicative markers or tags in structured data and documentation

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

    Followed by a capital letter

    np_acts-logits-general · gemini-2.0-flash

    renormalized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.72
    ]';
    -0.54
    />";
    -0.52
     “
    -0.52
     us
    -0.52
     me
    -0.51
     they
    -0.51
     stop
    -0.51
    +#+
    -0.51
     devoirs
    -0.49
    POSITIVE LOGITS
     poffible
    0.80
     myſelf
    0.78
     pleaſure
    0.77
     leſs
    0.73
     pixels
    0.72
     neceffary
    0.72
     ſtill
    0.70
     fevere
    0.70
     reaſon
    0.69
     ſmall
    0.67
    Act Density 0.173%

    No Known Activations