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

    Neuronpedia

    INDEX
    Explanations

    information related to categorization and classification of entities or data

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

    vectors, herself, affiliation, resin, variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.75
     للاسماء
    -0.73
     autorytatywna
    -0.64
    Tikang
    -0.59
    MLLoader
    -0.59
     utafitiHapana
    -0.59
    期刊论文
    -0.55
    Autoritní
    -0.55
     Chwiliwch
    -0.54
     незавершена
    -0.48
    POSITIVE LOGITS
    wapV
    0.52
     Administrativna
    0.45
    뀜
    0.42
     تكبرها
    0.41
    뀐
    0.40
    RectangleBorder
    0.39
    DrawerToggle
    0.38
    脚注の使い方
    0.38
    +#+
    0.37
    AutoModerator
    0.36
    Act Density 0.099%

    No Known Activations