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

    Neuronpedia

    INDEX
    Explanations

    punctuation/or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _o
    -0.07
    .home
    -0.07
    /tree
    -0.07
    ji
    -0.06
    _gs
    -0.06
     konu
    -0.06
    adol
    -0.06
    .vert
    -0.06
     physics
    -0.06
    ),
↵
    -0.06
    POSITIVE LOGITS
    ashington
    0.07
     prosince
    0.07
     آنلاین
    0.06
    態
    0.06
    _sh
    0.06
     believable
    0.06
     yayım
    0.06
     abruptly
    0.06
     Blizzard
    0.06
    VIDEO
    0.06
    Act Density 0.016%

    No Known Activations