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

    Neuronpedia

    INDEX
    Explanations

    seal of approval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    空间
    -0.07
    ่นเกม
    -0.06
     Gand
    -0.06
     KR
    -0.06
     Added
    -0.06
     hope
    -0.06
    thrown
    -0.06
    (IO
    -0.06
    �
    -0.06
     ас
    -0.06
    POSITIVE LOGITS
     Razor
    0.06
    antity
    0.06
     fillColor
    0.06
     ui
    0.06
     شود
    0.06
    .self
    0.06
    =utf
    0.06
     유지
    0.06
    orca
    0.06
     rizik
    0.06
    Act Density 0.064%

    No Known Activations