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

    Neuronpedia

    INDEX
    Explanations

    using or not using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    0.80
    。
    0.70
     it
    0.68
     if
    0.64
     that
    0.63
     some
    0.60
     for
    0.60
    ).
    0.60
     keperluan
    0.59
    )
    0.57
    POSITIVE LOGITS
    ദ്ധതി
    0.57
    三种
    0.56
     ત્રણ
    0.55
     ശക്ത
    0.55
    alarının
    0.54
    三大
    0.53
    Federal
    0.52
    enquête
    0.52
    Numerous
    0.52
     বারবার
    0.51
    Act Density 0.003%

    No Known Activations