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

    Neuronpedia

    INDEX
    Explanations

    phrases related to missing or lacking something

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

    any thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.54
    SequentialGroup
    -0.53
    endpush
    -0.52
    meja
    -0.48
    paravant
    -0.47
    WaitGroup
    -0.46
     embora
    -0.46
    それに
    -0.45
    NameInMap
    -0.43
     hyö
    -0.43
    POSITIVE LOGITS
     surla
    0.53
    abestanden
    0.49
     snippetHide
    0.48
    InitVars
    0.47
     nakalista
    0.46
    yntaxException
    0.41
    everything
    0.40
     Nada
    0.40
     المعيارى
    0.39
    一切
    0.38
    Act Density 0.030%

    No Known Activations