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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hardness
    -0.07
     must
    -0.06
    よ
    -0.06
     fallback
    -0.06
     Kerr
    -0.06
     walls
    -0.06
     rulers
    -0.06
     má
    -0.06
     parked
    -0.06
     Crypt
    -0.06
    POSITIVE LOGITS
     hect
    0.07
     setPage
    0.07
     покуп
    0.07
     dư�
    0.07
    oliberal
    0.07
     alınan
    0.06
     financier
    0.06
    /<
    0.06
    /Page
    0.06
     adversely
    0.06
    Act Density 0.037%

    No Known Activations