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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and greetings

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

    recent events or seeking help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.43
     Remember
    -0.38
    UrlResolution
    -0.35
     surprises
    -0.35
     eût
    -0.34
    enderror
    -0.34
     yapılır
    -0.34
     remember
    -0.33
    让你
    -0.32
     wirst
    -0.31
    POSITIVE LOGITS
     Recently
    0.75
    Recently
    0.75
     recently
    0.72
     recientemente
    0.70
    recently
    0.69
     seeking
    0.66
     recentemente
    0.65
    Seeking
    0.65
    parsedMessage
    0.64
    最近
    0.63
    Act Density 0.056%

    No Known Activations