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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Curriculum
    -0.08
    筱
    -0.07
    Ű
    -0.07
     componentWill
    -0.07
    ժ
    -0.07
    促
    -0.06
    ﳐ
    -0.06
     capacità
    -0.06
    曲
    -0.06
    홍
    -0.06
    POSITIVE LOGITS
    )];↵↵
    0.08
     Dust
    0.07
     meals
    0.07
     };↵↵
    0.07
     ................
    0.07
    :animated
    0.07
    oren
    0.07
    host
    0.07
    =>{↵
    0.07
     Cells
    0.06
    Act Density 0.003%

    No Known Activations