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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thirteen
    -0.07
    ActionPerformed
    -0.07
     himself
    -0.07
     Jim
    -0.07
    Ill
    -0.07
     tym
    -0.06
     eleven
    -0.06
    .cookie
    -0.06
     them
    -0.06
     ])
    -0.06
    POSITIVE LOGITS
     where
    0.18
    where
    0.14
     Where
    0.13
    Where
    0.11
    (where
    0.10
     WHERE
    0.10
     wherever
    0.09
     wherein
    0.09
     waar
    0.09
     hvor
    0.09
    Act Density 0.064%

    No Known Activations