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

    Neuronpedia

    INDEX
    Explanations

    rice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disappear
    -0.08
    !';↵
    -0.07
    综合素质
    -0.07
    outube
    -0.07
     einfach
    -0.07
     نفسه
    -0.07
    叛
    -0.07
    מחו
    -0.07
    Opera
    -0.07
    哪里
    -0.07
    POSITIVE LOGITS
    法规
    0.08
    phins
    0.07
    녂
    0.07
     Chatt
    0.07
    	row
    0.07
     enviar
    0.07
    .bio
    0.07
     MOST
    0.07
    GLfloat
    0.07
     hot
    0.07
    Act Density 0.007%

    No Known Activations