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

    Neuronpedia

    INDEX
    Explanations

    code and special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ян
    -0.07
     jeg
    -0.07
    "This
    -0.07
     продук
    -0.07
    aturity
    -0.07
     حر
    -0.06
    мя
    -0.06
    ɕ
    -0.06
    届毕业生
    -0.06
    慆
    -0.06
    POSITIVE LOGITS
    "&
    0.07
    情况来看
    0.07
    𝐋
    0.07
     CommandLine
    0.07
    £
    0.07
     awards
    0.07
    Extent
    0.06
    .devices
    0.06
     -=
    0.06
    _PH
    0.06
    Act Density 0.110%

    No Known Activations