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

    Neuronpedia

    INDEX
    Explanations

    Tobacco

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rumpe
    -0.09
    Ř
    -0.08
     yık
    -0.07
    虷
    -0.07
     hanya
    -0.07
    🄷
    -0.07
    朴
    -0.07
    структур
    -0.06
     chưa
    -0.06
    getY
    -0.06
    POSITIVE LOGITS
    (Message
    0.07
    );//
    0.07
    (flag
    0.07
    ificates
    0.07
     Lands
    0.07
    icates
    0.07
    Heroes
    0.06
    (plan
    0.06
     sofas
    0.06
    icate
    0.06
    Act Density 0.000%

    No Known Activations