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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the impact on people's lives

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

    life qualities and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     labeling
    -0.40
    prech
    -0.39
    都
    -0.39
    数
    -0.38
     succession
    -0.38
    repres
    -0.37
     Egon
    -0.37
     חיצוניים
    -0.37
    FlowLayout
    -0.36
     Restra
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.82
    +#+#
    0.74
     utafitiHapana
    0.61
    GEBURTSDATUM
    0.60
     življen
    0.58
    LIFE
    0.57
     życiu
    0.55
    aarrggbb
    0.53
    awtextra
    0.52
     życie
    0.51
    Act Density 0.011%

    No Known Activations