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

    Neuronpedia

    INDEX
    Explanations

    Chris

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    running
    -0.08
     ог
    -0.07
     weapon
    -0.07
     upwards
    -0.07
    是一
    -0.07
    关闭
    -0.07
    $',
    -0.07
     '"
    -0.07
     ingredient
    -0.07
     DW
    -0.06
    POSITIVE LOGITS
     comentarios
    0.07
    ่งชาต
    0.07
    Contrib
    0.06
    겠
    0.06
    tabl
    0.06
    Phys
    0.06
     BITS
    0.06
    TextChanged
    0.06
    utschein
    0.06
     earthqu
    0.06
    Act Density 0.001%

    No Known Activations