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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Law
    -0.07
     из
    -0.07
     psik
    -0.07
    Encrypt
    -0.07
     pprint
    -0.06
     дум
    -0.06
    خی
    -0.06
    :::::
    -0.06
    詩
    -0.06
     Эти
    -0.06
    POSITIVE LOGITS
    rocess
    0.07
    (boolean
    0.07
    .lua
    0.07
    orro
    0.06
    _SLOT
    0.06
     cz
    0.06
    avigate
    0.06
     pave
    0.06
    fest
    0.06
    角色
    0.06
    Act Density 0.083%

    No Known Activations