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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NAV
    -0.07
    -four
    -0.07
    Pot
    -0.07
    909
    -0.07
     autofocus
    -0.07
     き
    -0.06
    >Z
    -0.06
    outs
    -0.06
    执
    -0.06
    خاص
    -0.06
    POSITIVE LOGITS
     high
    0.08
    pragma
    0.07
    eneration
    0.06
    会议
    0.06
     legisl
    0.06
     conduit
    0.06
    arası
    0.06
    이슈
    0.06
     esi
    0.06
    (describing
    0.06
    Act Density 0.031%

    No Known Activations