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

    Neuronpedia

    INDEX
    Explanations

    im

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ủy
    -0.07
    )|(
    -0.06
    (ignore
    -0.06
    �습니다
    -0.06
    (be
    -0.06
     sino
    -0.06
     KeyboardInterrupt
    -0.06
     immersed
    -0.06
    (||
    -0.06
    ])+
    -0.06
    POSITIVE LOGITS
    Shock
    0.08
     kterou
    0.07
    ala
    0.07
    ALA
    0.07
    .feedback
    0.07
     Notre
    0.06
    ja
    0.06
    алог
    0.06
    칙
    0.06
    我们的
    0.06
    Act Density 0.442%

    No Known Activations