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

    Neuronpedia

    INDEX
    Explanations

    when introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अन्
    0.54
    estimate
    0.52
     செய்யப்பட்டு
    0.52
     छोर
    0.51
    ionych
    0.50
     Германия
    0.49
     Đức
    0.48
    िओ
    0.48
     दुर्भाग्य
    0.47
     کرتے
    0.47
    POSITIVE LOGITS
    오
    0.46
     breaches
    0.44
    礼
    0.43
    감
    0.42
    渴
    0.42
    宜
    0.40
    ለም
    0.40
    口
    0.40
    шена
    0.40
    ందో
    0.39
    Act Density 0.001%

    No Known Activations