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
     utilizando
    -0.07
     Grove
    -0.06
     ثلاث
    -0.06
     agosto
    -0.06
    博客
    -0.06
    ;k
    -0.06
     글
    -0.06
    堕
    -0.06
    udp
    -0.06
    Sprite
    -0.06
    POSITIVE LOGITS
    heritance
    0.07
    ()↵↵↵
    0.07
    stood
    0.07
    -P
    0.07
     lighting
    0.07
     intimate
    0.07
     Painter
    0.07
     ROUT
    0.07
     waiter
    0.07
     Father
    0.06
    Act Density 0.003%

    No Known Activations