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

    Neuronpedia

    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caf
    -0.07
     faker
    -0.07
     pop
    -0.07
     week
    -0.07
     realm
    -0.06
    children
    -0.06
     '{
    -0.06
     V
    -0.06
     enforcing
    -0.06
    似乎
    -0.06
    POSITIVE LOGITS
    Applied
    0.06
    akedirs
    0.06
    ilage
    0.06
    ous
    0.06
    ",__
    0.06
    ondrous
    0.06
     Humb
    0.06
    격
    0.06
     teal
    0.06
     söy
    0.06
    Act Density 0.000%

    No Known Activations