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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks typically found at the end of sentences

    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
    ulemon
    -0.52
     MainAxisSize
    -0.46
     tran
    -0.45
    tvguidetime
    -0.45
    bootstrapcdn
    -0.44
    cloudflare
    -0.44
     fing
    -0.44
    phrag
    -0.43
    tims
    -0.43
     ghoul
    -0.43
    POSITIVE LOGITS
    0.47
     antemano
    0.46
    ksessa
    0.44
     propOrder
    0.44
     nød
    0.44
     potrze
    0.43
    SharedDtor
    0.43
     Económica
    0.42
     creativos
    0.42
     szüks
    0.42
    Act Density 0.003%

    No Known Activations