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

    Neuronpedia

    INDEX
    Explanations

    last

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    احتمال
    -0.08
     =============================================================================↵
    -0.07
    mostat
    -0.07
    EditMode
    -0.07
     regulations
    -0.06
     super
    -0.06
     biased
    -0.06
     Parameters
    -0.06
    <Tag
    -0.06
     olduk
    -0.06
    POSITIVE LOGITS
     lul
    0.08
    ישי
    0.08
     créd
    0.08
     stif
    0.07
    uniq
    0.07
     Patty
    0.07
    十里
    0.07
    zell
    0.07
     مدريد
    0.07
     dashed
    0.07
    Act Density 0.015%

    No Known Activations