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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and connections in a mathematical or scientific context

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

    gerund and noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yszer
    -0.47
     oprot
    -0.46
    värr
    -0.45
     Kath
    -0.44
    <bos>
    -0.42
    VIAF
    -0.42
    ksesta
    -0.42
     larmes
    -0.40
     enfans
    -0.40
    datastore
    -0.40
    POSITIVE LOGITS
    ления
    0.71
    mation
    0.68
    mmation
    0.65
    нение
    0.64
    ation
    0.64
    eneration
    0.64
    zenie
    0.64
    entiation
    0.63
    ization
    0.63
    ление
    0.63
    Act Density 0.003%

    No Known Activations