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

    Neuronpedia

    INDEX
    Explanations

    Mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pokus
    -0.07
     contempt
    -0.07
    RAINT
    -0.06
    iesel
    -0.06
     evaluator
    -0.06
    .ht
    -0.06
    .Orientation
    -0.06
     bourgeois
    -0.06
     Simmons
    -0.06
     uncomment
    -0.06
    POSITIVE LOGITS
     oleh
    0.07
    정부
    0.07
    CLUSION
    0.06
    DH
    0.06
    歴
    0.06
    ionario
    0.06
    AppName
    0.06
    竜
    0.06
    _".$
    0.06
     그렇
    0.06
    Act Density 0.012%

    No Known Activations