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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to decision-making and certainty

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

    uncertainty or questioning

    np_acts-logits-general · gemini-2.0-flash

    whether or if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.71
     Cytometry
    -0.58
    好不容易
    -0.57
     समीक्षक
    -0.57
     Тогда
    -0.56
    Portale
    -0.55
    ussian
    -0.55
    anthene
    -0.54
    kowa
    -0.54
    odeficiency
    -0.54
    POSITIVE LOGITS
     whether
    3.95
    whether
    3.31
     Whether
    2.98
     WHETHER
    2.86
    Whether
    2.81
     apakah
    2.32
    是否
    2.16
     是否
    1.83
    是否有
    1.76
     آیا
    1.67
    Act Density 0.897%

    No Known Activations