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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("""↵
    -0.07
    /home
    -0.07
     Language
    -0.07
     IO
    -0.07
    su
    -0.06
    comfort
    -0.06
     exposure
    -0.06
    decorate
    -0.06
    ाज
    -0.06
    (Json
    -0.06
    POSITIVE LOGITS
    .selectedIndex
    0.06
     �
    0.06
    ButtonClick
    0.06
    paired
    0.06
     اصول
    0.06
     conductivity
    0.06
    ाइस
    0.06
     нем
    0.06
    ElementsByTagName
    0.06
     соверш
    0.06
    Act Density 0.004%

    No Known Activations