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

    Neuronpedia

    INDEX
    Explanations

    преимущества, прежде, предоставление

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prere
    0.52
     indexed
    0.50
     pre
    0.48
    Kau
    0.48
    beit
    0.46
    预
    0.46
    ZW
    0.46
    arnia
    0.44
     मौ
    0.44
    洺
    0.44
    POSITIVE LOGITS
    пят
    0.42
    обра
    0.39
    ференциа
    0.38
    до
    0.38
     образования
    0.38
     Fres
    0.37
    став
    0.37
    grado
    0.36
    tenant
    0.36
    තුරු
    0.36
    Act Density 0.003%

    No Known Activations