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

    Neuronpedia

    INDEX
    Explanations

    752

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dave
    -0.07
     diligence
    -0.06
    .repaint
    -0.06
    Priority
    -0.06
     Boss
    -0.06
     suprem
    -0.06
    asses
    -0.06
     orderly
    -0.06
    инку
    -0.06
    Pool
    -0.06
    POSITIVE LOGITS
    )↵↵↵↵↵↵↵↵
    0.07
     Aleppo
    0.07
    を作
    0.07
     souha
    0.07
     kişiler
    0.06
     розмі
    0.06
    _ASCII
    0.06
    ază
    0.06
     çoğu
    0.06
     xmlDoc
    0.06
    Act Density 0.000%

    No Known Activations