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

    Neuronpedia

    INDEX
    Explanations

    left

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harr
    -0.07
     Hav
    -0.07
     Heavy
    -0.07
     Reve
    -0.07
     Fo
    -0.06
     Bou
    -0.06
     졸
    -0.06
     DM
    -0.06
     Lear
    -0.06
     pe
    -0.06
    POSITIVE LOGITS
     left
    0.08
     remembering
    0.07
     LEFT
    0.06
     numberOfRows
    0.06
     кух
    0.06
     posledních
    0.06
    -Benz
    0.06
    (nextProps
    0.06
    слід
    0.06
    letion
    0.06
    Act Density 0.005%

    No Known Activations