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

    Neuronpedia

    INDEX
    Explanations

    the phrase "there's" or "there is" followed by various quantities or attributes

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating absence or limitation

    np_token-act-pair-logits · gpt-4o-mini

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تفصیلات
    -0.67
     Ause
    -0.58
    μβρίου
    -0.57
    lucid
    -0.57
    Бележки
    -0.55
     myſelf
    -0.54
     Suez
    -0.54
    Населення
    -0.53
     Escort
    -0.52
    qrst
    -0.52
    POSITIVE LOGITS
     only
    0.54
     zero
    0.52
    %)$
    0.49
    SqlSession
    0.47
     don
    0.47
    Alors
    0.45
     this
    0.45
     so
    0.44
     mapStateToProps
    0.44
     Only
    0.43
    Act Density 0.653%

    No Known Activations