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

    Neuronpedia

    INDEX
    Explanations

    gradients and backpropagation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＞
    -0.08
    ฤษภาคม
    -0.07
    uspend
    -0.07
    _BACKGROUND
    -0.07
    ày
    -0.06
     В
    -0.06
     swallowing
    -0.06
     Trot
    -0.06
    else
    -0.06
    Define
    -0.06
    POSITIVE LOGITS
    cff
    0.07
    ाम
    0.06
     }}>↵
    0.06
     screen
    0.06
    _minute
    0.06
     cleanly
    0.06
     ActionResult
    0.06
    ="#"
    0.06
    .elementAt
    0.06
     onChange
    0.06
    Act Density 0.020%

    No Known Activations