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

    Neuronpedia

    INDEX
    Explanations

    data visualization packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relocating
    -0.08
     пла
    -0.08
    NAS
    -0.07
    Cancellation
    -0.07
    nonce
    -0.07
     placing
    -0.07
    _terms
    -0.07
    pane
    -0.07
     перест
    -0.07
    pty
    -0.07
    POSITIVE LOGITS
    avait
    0.09
     swal
    0.07
    black
    0.07
    ательного
    0.07
     potenci
    0.07
    avadoc
    0.07
     д
    0.07
    -black
    0.07
     talál
    0.07
    �
    0.07
    Act Density 0.003%

    No Known Activations