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

    Neuronpedia

    INDEX
    Explanations

    name, com, load

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बृहस्पति
    0.71
     कोरबा
    0.65
    你看
    0.63
    여행
    0.62
    パール
    0.61
    ఫ
    0.61
    see
    0.61
    旅行
    0.61
    title
    0.60
    campfire
    0.60
    POSITIVE LOGITS
     红
    0.76
    臘
    0.75
     DEA
    0.74
    红
    0.74
     ICM
    0.74
     Informatics
    0.73
     WI
    0.72
     Switching
    0.71
     Apro
    0.71
    腊
    0.70
    Act Density 0.012%

    No Known Activations