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

    Neuronpedia

    INDEX
    Explanations

    packaged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Significant
    -0.08
     slik
    -0.07
     projectName
    -0.07
     significant
    -0.07
     stim
    -0.07
     demonstrated
    -0.06
     shadows
    -0.06
     exceeded
    -0.06
    Playing
    -0.06
     十
    -0.06
    POSITIVE LOGITS
    postal
    0.07
     khoản
    0.07
    poster
    0.06
    abela
    0.06
     Receipt
    0.06
     dislike
    0.06
    ーラ
    0.06
    Во
    0.06
     }):
    0.06
    ilyn
    0.06
    Act Density 0.010%

    No Known Activations