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

    Neuronpedia

    INDEX
    Explanations

    code, numbers, and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coleman
    -0.06
    _wo
    -0.06
    Int
    -0.06
     humanities
    -0.06
    lify
    -0.06
    ЛИ
    -0.06
    ря
    -0.06
    руют
    -0.06
     باش
    -0.06
     fastest
    -0.06
    POSITIVE LOGITS
     Leben
    0.07
    =back
    0.06
    actus
    0.06
     bahsed
    0.06
    ileceğini
    0.06
    �
    0.06
    utzer
    0.06
    ควบค
    0.06
     controle
    0.06
    processors
    0.06
    Act Density 0.000%

    No Known Activations