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

    Neuronpedia

    INDEX
    Explanations

    representing what are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     practised
    0.40
    лект
    0.40
    ন্তী
    0.39
     practising
    0.38
    ິງ
    0.36
    ந்த்
    0.35
    Clouds
    0.35
     globules
    0.35
    ptus
    0.34
    土
    0.34
    POSITIVE LOGITS
    َالَ
    0.40
     Mire
    0.37
    แฟ
    0.37
     Imagine
    0.36
    ZC
    0.35
     RTL
    0.35
    imethyl
    0.35
     Leng
    0.35
    sgál
    0.35
    visa
    0.35
    Act Density 0.000%

    No Known Activations