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

    Neuronpedia

    INDEX
    Explanations

    "/>"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     height
    -0.08
     aspect
    -0.07
    _ips
    -0.07
     engages
    -0.07
     Foreign
    -0.07
    oun
    -0.07
     scheme
    -0.06
    ht
    -0.06
    cepts
    -0.06
    tone
    -0.06
    POSITIVE LOGITS
    Closed
    0.07
    クラブ
    0.06
     bere
    0.06
    ;.
    0.06
    :.
    0.06
     раніше
    0.06
    _ROOM
    0.06
     문의
    0.06
    载
    0.06
    _RES
    0.06
    Act Density 0.003%

    No Known Activations