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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and references to amounts or quantities

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

    much of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    terape
    -0.47
     Yogi
    -0.44
     those
    -0.44
     themselves
    -0.43
     centen
    -0.43
    FirstResponder
    -0.41
    jMenu
    -0.41
     bouch
    -0.39
     realiz
    -0.38
     constitutions
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.66
     صوتيه
    0.64
     information
    0.61
     المعيارى
    0.60
     informatie
    0.60
     BorderSide
    0.59
    tanleria
    0.59
    OGND
    0.59
    stuk
    0.58
     bilgi
    0.57
    Act Density 0.027%

    No Known Activations