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

    Neuronpedia

    INDEX
    Explanations

    code and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     len
    -0.07
    cks
    -0.07
    =len
    -0.07
    _USART
    -0.07
     августа
    -0.06
    렸
    -0.06
     revolutions
    -0.06
    _Un
    -0.06
     таким
    -0.06
    ίζει
    -0.06
    POSITIVE LOGITS
     leaving
    0.07
    Moved
    0.06
    ussy
    0.06
     termed
    0.06
     得
    0.06
     энерг
    0.06
    anlar
    0.06
    績
    0.06
     leave
    0.06
     educate
    0.06
    Act Density 0.001%

    No Known Activations