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

    Neuronpedia

    INDEX
    Explanations

    finding resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昆仑
    -0.08
     Gospel
    -0.07
    tg
    -0.07
     grande
    -0.06
    第三者
    -0.06
     وحت
    -0.06
    unar
    -0.06
    (copy
    -0.06
     المباشر
    -0.06
    equ
    -0.06
    POSITIVE LOGITS
    有用
    0.08
    绋
    0.07
     Rot
    0.07
     crit
    0.07
    Beta
    0.07
    满意
    0.07
    工作
    0.07
     AssemblyDescription
    0.07
     �
    0.07
    roupon
    0.06
    Act Density 0.116%

    No Known Activations