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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通用
    -0.07
    Fo
    -0.07
    -order
    -0.07
     cell
    -0.07
     schema
    -0.07
    BALL
    -0.07
    ()])↵
    -0.07
     played
    -0.07
    sci
    -0.07
    )NULL
    -0.07
    POSITIVE LOGITS
    usaha
    0.07
    onne
    0.06
    加工
    0.06
    osi
    0.06
     cruel
    0.06
    🧜
    0.06
    㠓
    0.06
    ῴ
    0.06
     guessing
    0.06
     Maar
    0.06
    Act Density 0.032%

    No Known Activations