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

    Neuronpedia

    INDEX
    Explanations

    close to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेटिक
    0.88
     tmux
    0.86
     doors
    0.84
    ="("
    0.83
     заключа
    0.83
    ปิด
    0.81
    imized
    0.81
     Closed
    0.81
     closed
    0.80
    Closed
    0.80
    POSITIVE LOGITS
    洗い
    1.04
    rope
    1.02
     współprac
    1.01
     shave
    0.99
    বী
    0.99
    knit
    0.99
    chalk
    0.96
    proximity
    0.91
     सटे
    0.90
     بخ
    0.90
    Act Density 0.049%

    No Known Activations