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

    Neuronpedia

    INDEX
    Explanations

    philosophical or speculative language, particularly related to certainty and assumptions

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

    Adverbs indicating uncertainty or common knowledge

    np_acts-logits-general · gemini-2.0-flash

    qualifying or general adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    selaer
    -0.71
    fillType
    -0.66
    Aholisi
    -0.64
    AnimationsModule
    -0.64
    ReusableCell
    -0.61
     GenerationType
    -0.60
     finalement
    -0.57
     يتيمه
    -0.56
    IonicModule
    -0.56
    ISupport
    -0.55
    POSITIVE LOGITS
    DockStyle
    0.72
    mente
    0.68
     heller
    0.67
    ً
    0.64
    omani
    0.63
    情况下
    0.61
    #__
    0.61
     []:
    0.60
    amente
    0.60
     speaking
    0.59
    Act Density 0.402%

    No Known Activations