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

    Neuronpedia

    INDEX
    Explanations

    Plus/minus signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     REGISTER
    -0.10
    REGISTER
    -0.09
    ▬
    -0.09
    /Register
    -0.08
    _REGISTER
    -0.08
     leta
    -0.08
    �
    -0.08
    (Register
    -0.08
    (JFrame
    -0.08
    (Command
    -0.08
    POSITIVE LOGITS
    ింప
    0.07
    క్�
    0.07
     sair
    0.07
    0.07
     solo
    0.07
    0.07
    mea
    0.07
     muti
    0.07
     Sich
    0.07
     putas
    0.07
    Act Density 0.123%
    No Known Activations