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

    Neuronpedia

    INDEX
    Explanations

    Expanding algebraic expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wheel
    -0.08
     Wheel
    -0.07
     själ
    -0.07
     cult
    -0.07
    EDGE
    -0.07
    инок
    -0.07
    VOICE
    -0.07
     Flick
    -0.07
    ら
    -0.07
    ttps
    -0.07
    POSITIVE LOGITS
     DAT
    0.08
     iniciativa
    0.08
    etan
    0.08
     Rutgers
    0.08
    Proj
    0.07
     ah
    0.07
     Gloucester
    0.07
     Ashley
    0.07
     Heinz
    0.07
     الخط
    0.07
    Act Density 0.303%

    No Known Activations