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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ques
    -0.07
    聘
    -0.07
     gg
    -0.07
     říj
    -0.07
     Effects
    -0.07
     judgment
    -0.07
    Recognition
    -0.07
     betrayal
    -0.07
     hitters
    -0.06
     poisonous
    -0.06
    POSITIVE LOGITS
     студ
    0.07
    [:,
    0.06
    ывается
    0.06
     zastav
    0.06
    ：</
    0.06
    urlpatterns
    0.06
    ,$_
    0.06
     Glow
    0.05
    .Open
    0.05
    oute
    0.05
    Act Density 0.005%

    No Known Activations