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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special symbols within text

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

    sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     res
    -0.29
     restantes
    -0.28
    Nonce
    -0.28
     partis
    -0.28
    fileName
    -0.27
    越好
    -0.27
    的做法
    -0.27
     pamoja
    -0.26
     items
    -0.26
     hing
    -0.26
    POSITIVE LOGITS
    specifically
    0.78
    Personendaten
    0.76
    Specifically
    0.75
     anzi
    0.71
    LookAnd
    0.71
     Specifically
    0.70
    albeit
    0.70
     причем
    0.68
     LOTS
    0.68
    Lots
    0.68
    Act Density 0.105%

    No Known Activations