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

    Neuronpedia

    INDEX
    Explanations

    fixed sticky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mil
    -0.07
    phanumeric
    -0.07
    kok
    -0.06
     exceptional
    -0.06
     　 　 　 　
    -0.06
     avg
    -0.06
    етич
    -0.06
    iliation
    -0.06
    真的
    -0.06
     SQ
    -0.06
    POSITIVE LOGITS
     ost
    0.07
     locked
    0.07
    inside
    0.06
    avit
    0.06
     разных
    0.06
    \Lib
    0.06
     asp
    0.06
    -U
    0.06
    >:
    0.06
    .POST
    0.06
    Act Density 0.005%

    No Known Activations