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

    Neuronpedia

    INDEX
    Explanations

    leading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bread
    -0.07
    证明
    -0.06
    `${
    -0.06
    (choices
    -0.06
    /Z
    -0.06
    	print
    -0.06
    otive
    -0.06
    Brightness
    -0.06
     Cowboys
    -0.06
     stitch
    -0.06
    POSITIVE LOGITS
    dp
    0.07
    99
    0.06
    issenschaft
    0.06
    ﻟ
    0.06
    Performance
    0.06
    ��글
    0.06
    _workflow
    0.06
     감
    0.06
    ůže
    0.06
    社区
    0.06
    Act Density 0.003%

    No Known Activations