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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .raise
    -0.07
    izen
    -0.06
    osyal
    -0.06
    (events
    -0.06
    Reward
    -0.06
     tradi
    -0.06
    늘
    -0.06
     Legacy
    -0.06
    Limited
    -0.06
    less
    -0.06
    POSITIVE LOGITS
     type
    0.09
    啊
    0.08
     '',
    0.07
     messing
    0.07
     Ct
    0.07
    >/
    0.07
    .withOpacity
    0.07
     genre
    0.06
     spos
    0.06
     Plates
    0.06
    Act Density 0.017%

    No Known Activations