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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VIS
    -0.07
     slime
    -0.07
    _returns
    -0.06
    ryptography
    -0.06
    azing
    -0.06
     tester
    -0.06
    риг
    -0.06
    _possible
    -0.06
    _Reference
    -0.06
    ById
    -0.06
    POSITIVE LOGITS
     đến
    0.07
    ,opt
    0.07
     erm
    0.06
     defaultCenter
    0.06
    .visibility
    0.06
     هم
    0.06
    .ticket
    0.06
    ,min
    0.06
    +%
    0.06
     viết
    0.06
    Act Density 0.012%

    No Known Activations