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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wert
    -0.07
     Giants
    -0.06
    perial
    -0.06
    čast
    -0.06
    >d
    -0.06
     swe
    -0.06
    Inject
    -0.06
    -k
    -0.06
    準
    -0.06
    	Mono
    -0.06
    POSITIVE LOGITS
    _SUPPORT
    0.07
     خلق
    0.06
     avail
    0.06
     外部リンク
    0.06
     BİL
    0.06
    取得
    0.06
     collage
    0.06
     pouvez
    0.06
     mạng
    0.06
    MN
    0.06
    Act Density 0.019%

    No Known Activations