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

    Neuronpedia

    INDEX
    Explanations

    Units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emple
    -0.07
     Sevilla
    -0.07
     prostitu
    -0.07
     biri
    -0.07
    жди
    -0.07
    оги
    -0.06
    ۳۵
    -0.06
     filmpjes
    -0.06
    rown
    -0.06
    ประโย
    -0.06
    POSITIVE LOGITS
     **/↵↵
    0.06
    (skip
    0.06
    BF
    0.06
     gson
    0.06
    (schema
    0.06
    Last
    0.05
     releases
    0.05
    (fields
    0.05
     champ
    0.05
     世界
    0.05
    Act Density 0.021%

    No Known Activations