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

    Neuronpedia

    INDEX
    Explanations

    modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chip
    -0.08
     áll
    -0.07
     τελ
    -0.07
     balls
    -0.07
     Trib
    -0.07
    ILON
    -0.07
    eldo
    -0.06
     pronounced
    -0.06
     включ
    -0.06
     sce
    -0.06
    POSITIVE LOGITS
    mh
    0.07
     modern
    0.07
     Modern
    0.07
    _DYNAMIC
    0.07
    _HIGH
    0.07
     田
    0.06
     wik
    0.06
    otypical
    0.06
     सव
    0.06
    .order
    0.06
    Act Density 0.008%

    No Known Activations