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

    Neuronpedia

    INDEX
    Explanations

    cript

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kos
    -0.06
     cereal
    -0.06
     memor
    -0.06
    -0.06
    Federal
    -0.06
    56
    -0.06
     tolerated
    -0.06
     nailed
    -0.06
    endance
    -0.06
     installation
    -0.06
    POSITIVE LOGITS
     Caribbean
    0.07
     Liên
    0.07
     Marketable
    0.07
     LP
    0.07
    лика
    0.07
    _TI
    0.06
     nové
    0.06
    迅
    0.06
    .How
    0.06
    #Region
    0.06
    Act Density 0.005%

    No Known Activations