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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    掌柜
    -0.09
    ?p
    -0.08
    མ
    -0.07
    贴近
    -0.07
    一切都是
    -0.07
    Reverse
    -0.07
    تعب
    -0.07
     treasury
    -0.07
    缧
    -0.07
    leared
    -0.07
    POSITIVE LOGITS
     Participants
    0.07
     MacOS
    0.07
     final
    0.06
    工业园
    0.06
     NM
    0.06
     кат
    0.06
    广播电视
    0.06
    leşme
    0.06
     å
    0.06
     Jong
    0.06
    Act Density 0.003%

    No Known Activations