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

    Neuronpedia

    INDEX
    Explanations

    drawing/graphics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KM
    -0.07
     coroutine
    -0.07
     дос
    -0.07
    eterminate
    -0.07
    gado
    -0.06
     Dy
    -0.06
    倒
    -0.06
     pts
    -0.06
     له
    -0.06
     natürlich
    -0.06
    POSITIVE LOGITS
    <{↵
    0.06
     Homeland
    0.06
    >Select
    0.06
    _DL
    0.06
    sty
    0.06
    ))==
    0.06
     lesbienne
    0.06
    ;}
↵
    0.06
     "==
    0.06
     RFC
    0.06
    Act Density 0.080%

    No Known Activations