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

    Neuronpedia

    INDEX
    Explanations

    Code plot label rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meric
    -0.08
     encycl
    -0.08
     deviation
    -0.08
    pure
    -0.07
    Games
    -0.07
    Pure
    -0.07
    games
    -0.07
    .Constants
    -0.07
     pure
    -0.07
     [])↵↵
    -0.07
    POSITIVE LOGITS
    日期
    0.09
     xa
    0.09
    .date
    0.09
    jeć
    0.09
     തീയ
    0.09
     Rotate
    0.08
     తేద
    0.08
    .strftime
    0.08
    strftime
    0.08
    .Date
    0.08
    Act Density 0.001%

    No Known Activations