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

    Neuronpedia

    INDEX
    Explanations

    code management

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jn
    -0.07
    (MenuItem
    -0.07
    setProperty
    -0.07
     Dữ
    -0.07
    (topic
    -0.07
     Minority
    -0.06
     Everyone
    -0.06
    	catch
    -0.06
     خارجية
    -0.06
    itting
    -0.06
    POSITIVE LOGITS
    吸
    0.08
     برخ
    0.07
     truy
    0.07
     vận
    0.06
     Hose
    0.06
    ocy
    0.06
     desper
    0.06
     дод
    0.06
     fel
    0.06
     종
    0.06
    Act Density 0.014%

    No Known Activations