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

    Neuronpedia

    INDEX
    Explanations

    this/'s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (**
    -0.07
     Fallout
    -0.06
     faith
    -0.06
     elapsedTime
    -0.06
    -se
    -0.06
    _ASSERT
    -0.06
    惊
    -0.06
    .expand
    -0.06
     深
    -0.06
     Funny
    -0.06
    POSITIVE LOGITS
    鮮
    0.06
     rop
    0.06
     rá
    0.06
    ecektir
    0.06
    
    0.06
     Sno
    0.06
    ＼
    0.06
     amateur
    0.06
     pared
    0.06
     системи
    0.06
    Act Density 0.075%

    No Known Activations