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

    Neuronpedia

    INDEX
    Explanations

    syntax and structural elements of programming code

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

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.76
    Personendaten
    -0.76
    :✨
    -0.68
    RegressionTest
    -0.68
     الحره
    -0.66
    ⤹
    -0.64
     betweenstory
    -0.64
    GraphicsUnit
    -0.63
     Réponses
    -0.62
    Portály
    -0.61
    POSITIVE LOGITS
    AccessorTable
    0.36
     betrekking
    0.31
     stöd
    0.31
     chrétien
    0.29
     stát
    0.29
     Volkes
    0.29
     techniczne
    0.28
     pengar
    0.28
     así
    0.28
    ikyuu
    0.28
    Act Density 0.002%

    No Known Activations