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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    に行
    -0.07
    attles
    -0.07
     erhalten
    -0.07
    Û
    -0.07
    GOP
    -0.06
    ắ
    -0.06
     damage
    -0.06
     Dop
    -0.06
    capacity
    -0.06
     Sergey
    -0.06
    POSITIVE LOGITS
     Usa
    0.07
    ycled
    0.07
     crumbs
    0.07
     LSD
    0.06
     Inside
    0.06
     Illustrator
    0.06
    META
    0.06
     Malcolm
    0.06
    Speaker
    0.06
    ('<
    0.06
    Act Density 0.020%

    No Known Activations