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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shapes
    -0.07
    Continuous
    -0.07
    ле
    -0.07
    .presentation
    -0.06
    opleft
    -0.06
     Err
    -0.06
    .cs
    -0.06
     world
    -0.06
     bên
    -0.06
     Paradise
    -0.06
    POSITIVE LOGITS
     eruption
    0.07
    된
    0.06
    //----------------------------------------------------------------------------↵
    0.06
     وصل
    0.06
    inue
    0.06
     UserType
    0.06
    часно
    0.06
     поба
    0.06
    ～↵↵
    0.06
    .Embed
    0.06
    Act Density 0.007%

    No Known Activations