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

    Neuronpedia

    INDEX
    Explanations

    episode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Copenhagen
    -0.07
    597
    -0.07
    935
    -0.07
    Sp
    -0.06
    щими
    -0.06
    不存在
    -0.06
     التح
    -0.06
    ятно
    -0.06
     Buk
    -0.06
     Service
    -0.06
    POSITIVE LOGITS
    _wrapper
    0.07
    _typ
    0.06
    cip
    0.06
    鄉
    0.06
    illusion
    0.06
    kla
    0.06
     Holidays
    0.06
    _ped
    0.06
     vpn
    0.06
    .CLASS
    0.05
    Act Density 0.061%

    No Known Activations