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

    Neuronpedia

    INDEX
    Explanations

    Improving, maintaining, making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мет
    0.48
    ме
    0.47
    ника
    0.47
    ну
    0.46
    ни
    0.46
    кра
    0.46
    イオン
    0.45
    पत्र
    0.45
    クラ
    0.44
    英國
    0.44
    POSITIVE LOGITS
    kev
    0.54
     nad
    0.53
     elucidated
    0.48
     laag
    0.48
    Ma
    0.46
     bei
    0.45
    D
    0.45
    㕶
    0.44
    Gew
    0.44
     köl
    0.44
    Act Density 0.000%

    No Known Activations