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

    Neuronpedia

    INDEX
    Explanations

    get run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UNDER
    -0.07
    /sn
    -0.07
    钟
    -0.07
    řik
    -0.06
    選択
    -0.06
    <T
    -0.06
    Blocking
    -0.06
    ervlet
    -0.06
    उत
    -0.06
     Ç
    -0.06
    POSITIVE LOGITS
     chap
    0.07
    (today
    0.06
     Avg
    0.06
    -signed
    0.06
     sweetheart
    0.06
     toughness
    0.06
     units
    0.06
     clinicians
    0.06
     tripod
    0.06
     bran
    0.06
    Act Density 0.003%

    No Known Activations