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

    Neuronpedia

    INDEX
    Explanations

    Linear Algebra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    In
    -0.07
    ρί
    -0.07
     덤프
    -0.07
     Default
    -0.07
     lesbian
    -0.07
     In
    -0.06
    ивает
    -0.06
     endoth
    -0.06
    est
    -0.06
     tone
    -0.06
    POSITIVE LOGITS
    emons
    0.07
     😉
    0.07
    ظٹط
    0.07
    isper
    0.06
     responseData
    0.06
     sanki
    0.06
    eyJ
    0.06
    irket
    0.06
    .isHidden
    0.06
     kesinlikle
    0.06
    Act Density 0.031%

    No Known Activations