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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ικοί
    -0.07
    ický
    -0.07
     opat
    -0.07
    )size
    -0.07
     tř
    -0.06
     moden
    -0.06
     अगस
    -0.06
    SOLE
    -0.06
     Čer
    -0.06
     dny
    -0.06
    POSITIVE LOGITS
     Maiden
    0.07
     velocity
    0.07
     Kitt
    0.07
     Collective
    0.07
    sonian
    0.06
    played
    0.06
    erral
    0.06
    матрива
    0.06
     bức
    0.06
     Auf
    0.06
    Act Density 0.018%

    No Known Activations