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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Menu
    -0.08
     Gas
    -0.07
    His
    -0.07
     downward
    -0.07
     say
    -0.07
    أ
    -0.07
    122
    -0.07
    片
    -0.07
    �어
    -0.06
    manage
    -0.06
    POSITIVE LOGITS
     предполаг
    0.07
     encount
    0.07
     spared
    0.06
    MN
    0.06
     xp
    0.06
     errorCallback
    0.06
     createElement
    0.06
     लगभग
    0.06
     giochi
    0.06
    coeff
    0.06
    Act Density 0.027%

    No Known Activations