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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instituted
    -0.08
     生
    -0.07
     لك
    -0.06
    (D
    -0.06
     Quad
    -0.06
     ucfirst
    -0.06
    .protocol
    -0.06
     vrouw
    -0.06
     feels
    -0.06
     Roland
    -0.06
    POSITIVE LOGITS
     iktidar
    0.07
     مى
    0.07
     HelloWorld
    0.07
    __
    0.07
    intro
    0.07
     bal
    0.06
    中に
    0.06
    芝
    0.06
    \View
    0.06
    จะต
    0.06
    Act Density 0.001%

    No Known Activations