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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "sync
    -0.07
     rue
    -0.07
    .navigate
    -0.07
    _For
    -0.06
    写道
    -0.06
     slee
    -0.06
     ==↵
    -0.06
    (Key
    -0.06
     Kurd
    -0.06
     pym
    -0.06
    POSITIVE LOGITS
    ----------
    0.08
    ضع
    0.07
     אזר
    0.07
    "];
↵
    0.07
    عنا
    0.07
    ℭ
    0.07
    샙
    0.06
    formatter
    0.06
    ỉnh
    0.06
    خص
    0.06
    Act Density 0.001%

    No Known Activations