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

    Neuronpedia

    INDEX
    Explanations

    Newbury/Newburyport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iy
    -0.08
    た
    -0.07
     ≤
    -0.07
    client
    -0.06
    Islam
    -0.06
     подав
    -0.06
    Rows
    -0.06
    Similarly
    -0.06
     plutôt
    -0.06
    jej
    -0.06
    POSITIVE LOGITS
    ATURE
    0.07
     Osborne
    0.07
    age
    0.07
     impover
    0.07
     purported
    0.06
    ford
    0.06
    مبر
    0.06
     IB
    0.06
    ONY
    0.06
    umber
    0.06
    Act Density 0.005%

    No Known Activations