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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or planned actions, particularly those starting with "we will" or similar constructs

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

    In this review we examine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.64
    -0.61
     يتيمه
    -0.56
    ModelSerializer
    -0.54
     Signalez
    -0.51
    astéroïdes
    -0.49
    SequentialGroup
    -0.47
    الإنجليزية
    -0.47
    keyColumn
    -0.44
    Ծանոթ
    -0.44
    POSITIVE LOGITS
     Vle
    0.40
     vPvB
    0.35
    postId
    0.33
     herein
    0.32
    オス
    0.32
    vre
    0.32
    TintMode
    0.32
     TODAY
    0.32
     Böh
    0.32
     today
    0.31
    Act Density 0.038%

    No Known Activations