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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ə
    -0.08
    副总裁
    -0.08
     wir
    -0.08
    ORE
    -0.07
     founders
    -0.07
    Or
    -0.07
     Co
    -0.07
    /arch
    -0.07
    Que
    -0.07
    onder
    -0.07
    POSITIVE LOGITS
    ᯙ
    0.07
    grave
    0.06
    㛚
    0.06
    =label
    0.06
    (vp
    0.06
    wf
    0.06
     Jeżeli
    0.06
     وأن
    0.06
     ان
    0.06
    ultip
    0.06
    Act Density 0.103%

    No Known Activations