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

    Neuronpedia

    INDEX
    Explanations

    par

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keen
    -0.06
     cí
    -0.06
    |x
    -0.06
    Picture
    -0.06
    竜
    -0.06
    uil
    -0.06
    _sphere
    -0.06
    되지
    -0.06
     아니
    -0.06
    588
    -0.06
    POSITIVE LOGITS
    /pp
    0.07
    (Const
    0.07
    سات
    0.07
    (each
    0.06
     Marr
    0.06
    airs
    0.06
    //---------------------------------------------------------------------------↵
    0.06
    _NT
    0.06
     McCl
    0.06
    /shared
    0.06
    Act Density 0.004%

    No Known Activations