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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genauso
    0.38
    㥆
    0.38
    𝖐
    0.36
    тивность
    0.36
    NameValuePair
    0.35
     জুটি
    0.35
    顷
    0.34
    жом
    0.34
    ஷா
    0.34
    舴
    0.33
    POSITIVE LOGITS
     related
    4.25
     Related
    3.78
    related
    3.72
    Related
    3.66
     relacionado
    3.52
     relacionados
    3.44
     relacionadas
    3.36
     relacionada
    3.36
     관련
    3.31
    関連
    3.30
    Act Density 0.181%

    No Known Activations