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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    references to elapsed-time expressions indicating something happened in the past

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    -Origin
    -0.06
     koneč
    -0.06
    -On
    -0.06
     erected
    -0.06
    �nh
    -0.06
    rightness
    -0.06
     hotspot
    -0.05
    Smooth
    -0.05
     thần
    -0.05
    极
    -0.05
    POSITIVE LOGITS
    dense
    0.06
     consumer
    0.06
     <$
    0.06
     such
    0.06
     gros
    0.06
     pops
    0.06
    <c
    0.06
    sem
    0.06
    лара
    0.06
    ")},↵
    0.06
    Act Density 1.562%

    No Known Activations