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

    Neuronpedia

    INDEX
    Explanations

    strong opinions and assertions about practices or events

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

    with the exception of all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.67
     actionPerformed
    -0.54
    BeginContext
    -0.52
     الرياضيه
    -0.52
    Portail
    -0.50
     CreateTagHelper
    -0.50
    rrggbb
    -0.47
    WithIOException
    -0.47
    adona
    -0.45
     nakalista
    -0.43
    POSITIVE LOGITS
     unless
    0.54
    Unless
    0.54
     AppCompat
    0.52
     Unless
    0.51
     except
    0.49
    Except
    0.47
    unless
    0.45
    以外は
    0.43
    printStats
    0.42
     kecuali
    0.42
    Act Density 0.091%

    No Known Activations