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

    Neuronpedia

    INDEX
    Explanations

    late 2023/early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вні
    0.38
     July
    0.35
    Division
    0.35
     senjata
    0.34
     инструментов
    0.34
     pre
    0.33
     September
    0.33
     settembre
    0.33
     فناوری
    0.33
     précisément
    0.33
    POSITIVE LOGITS
     સમજ
    0.44
    彘
    0.41
    つつ
    0.40
    సక్తి
    0.40
     требует
    0.40
     voici
    0.39
     wymag
    0.39
     pragmatic
    0.39
     Uda
    0.39
     Dol
    0.39
    Act Density 0.008%

    No Known Activations