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

    Neuronpedia

    INDEX
    Explanations

    sentence terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍢
    0.86
     সমস্যাবলী
    0.84
     ؟
    0.82
    ؛
    0.80
    на
    0.80
    there
    0.80
     જરૂ
    0.80
    🔡
    0.80
    ানুভূতি
    0.79
    ،
    0.79
    POSITIVE LOGITS
     buổi
    0.79
     protest
    0.70
     기존
    0.66
    इसके
    0.64
     bunun
    0.64
     urban
    0.63
     tự
    0.63
     그
    0.63
     jonka
    0.63
     böyle
    0.62
    Act Density 0.001%

    No Known Activations