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

    Neuronpedia

    INDEX
    Explanations

    basically

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虑
    -0.08
    apper
    -0.07
     Jas
    -0.06
     Been
    -0.06
     Cairo
    -0.06
    呕吐
    -0.06
    (serv
    -0.06
     RETURN
    -0.06
     списка
    -0.06
     לקחת
    -0.06
    POSITIVE LOGITS
     Texture
    0.07
    share
    0.07
    inflate
    0.07
    ☁
    0.07
    ług
    0.07
    相关内容
    0.07
     ue
    0.06
    values
    0.06
     standards
    0.06
    (fe
    0.06
    Act Density 0.005%

    No Known Activations