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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zept
    -0.77
    监督
    -0.74
    鷹
    -0.66
    伟大
    -0.66
    ego
    -0.65
    egt
    -0.65
    Ал
    -0.65
     烤
    -0.65
    requently
    -0.65
    mok
    -0.64
    POSITIVE LOGITS
     iceberg
    0.69
     Vichy
    0.66
     Imp
    0.65
     Harding
    0.65
    ^@
    0.64
     Typ
    0.64
     cove
    0.63
    Fg
    0.63
     IMPROVEMENT
    0.62
    estudi
    0.61
    Act Density 0.066%

    No Known Activations