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

    Neuronpedia

    INDEX
    Explanations

    dates and numbers

    np_max-act · gemini-2.0-flash

    find vector magnitudes and dot products.

    oai_token-act-pair · gpt-5-nanoTriggered by @tatsatx
    New Auto-Interp
    Negative Logits
    Â
    -0.13
     â
    -0.12
    â
    -0.11
    <|reserved_200016|>
    -0.10
     
    -0.10
    Ã
    -0.09
    Î
    -0.09
     Ã
    -0.09
     Ï
    -0.09
    ...
    -0.08
    POSITIVE LOGITS
    ↵                ↵
    0.07
     lotus
    0.06
    لد
    0.06
     Highest
    0.06
    VG
    0.06
    Huge
    0.06
     જોકે
    0.06
    ರವ
    0.06
     Ensure
    0.06
     대부분
    0.06
    Act Density 27.683%

    No Known Activations