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

    Neuronpedia

    INDEX
    Explanations

    clause explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     της
    0.50
     zove
    0.36
     түз
    0.36
    Trail
    0.36
     системи
    0.35
    Stein
    0.35
    Wert
    0.35
     دوره
    0.34
    Levels
    0.34
     बिल्डिंग
    0.34
    POSITIVE LOGITS
    ær
    0.42
     penyakit
    0.41
     odstr
    0.40
     дополнительные
    0.39
     avoir
    0.39
    问题
    0.38
    点头
    0.38
    भव
    0.37
     verwij
    0.37
    ecer
    0.37
    Act Density 0.003%

    No Known Activations