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

    Neuronpedia

    INDEX
    Explanations

    mount

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onz
    -0.07
     interstate
    -0.07
     initialization
    -0.07
     checklist
    -0.07
     sensitivity
    -0.07
     Steak
    -0.07
     forg
    -0.07
     pastor
    -0.07
     cords
    -0.07
     olmadığ
    -0.07
    POSITIVE LOGITS
    -written
    0.07
    绚
    0.07
    atural
    0.07
    elaide
    0.07
     Books
    0.07
    xfff
    0.07
    服务
    0.07
    我去
    0.07
    イラ
    0.07
    uttgart
    0.06
    Act Density 0.045%

    No Known Activations