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

    Neuronpedia

    INDEX
    Explanations

    document formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internet
    -0.08
     Krak
    -0.08
    -0.08
     électrique
    -0.08
     hình
    -0.07
    Connectivity
    -0.07
     grin
    -0.07
    -wide
    -0.07
     Henri
    -0.07
     diya
    -0.07
    POSITIVE LOGITS
     genees
    0.09
     Verse
    0.08
     طبی
    0.08
    -spacing
    0.08
     હોવાથી
    0.07
    文
    0.07
    spacing
    0.07
     હોવાનું
    0.07
    ######
    0.07
    商务
    0.07
    Act Density 0.001%
    No Known Activations