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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :x
    -0.07
     decoder
    -0.07
    Roll
    -0.07
     tree
    -0.07
     receptive
    -0.06
     balancing
    -0.06
    xlabel
    -0.06
    }):
    -0.06
     testimony
    -0.06
    ..↵↵
    -0.06
    POSITIVE LOGITS
     رشد
    0.07
     группы
    0.07
    _WEAPON
    0.07
     زیاد
    0.06
    (load
    0.06
     Assembly
    0.06
    _workflow
    0.06
     编
    0.06
     větší
    0.06
     pageNum
    0.06
    Act Density 0.018%

    No Known Activations