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

    Neuronpedia

    INDEX
    Explanations

    permutation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towers
    -0.07
     Fritz
    -0.07
     pointers
    -0.07
     duty
    -0.07
     kun
    -0.07
    rays
    -0.07
    Center
    -0.07
     crosses
    -0.07
    Ray
    -0.07
     сім
    -0.06
    POSITIVE LOGITS
     электри
    0.08
     постоянно
    0.06
     AppleWebKit
    0.06
     перв
    0.06
    _BT
    0.06
     neut
    0.06
     yayım
    0.06
    жно
    0.06
    Autom
    0.06
    BMW
    0.06
    Act Density 0.014%

    No Known Activations