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

    Neuronpedia

    INDEX
    Explanations

    key functions or methods in programming context

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

    Code, equations, or non-English words

    np_acts-logits-general · gemini-2.0-flash

    highlighted rows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    -0.49
     trung
    -0.47
     kurang
    -0.46
     now
    -0.45
     at
    -0.44
     today
    -0.43
     […]
    -0.42
     on
    -0.41
    jooq
    -0.41
     and
    -0.41
    POSITIVE LOGITS
     purpoſe
    1.12
     Theſe
    1.02
    ſelves
    1.01
     Monfieur
    1.00
     ſtate
    0.99
    ſelf
    0.99
     myſelf
    0.99
     ſte
    0.97
     greateſt
    0.97
     pleaſure
    0.95
    Act Density 0.406%

    No Known Activations