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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ingle
    0.68
    Os
    0.67
     রহিম
    0.66
    ounid
    0.64
     os
    0.64
    ook
    0.63
     single
    0.61
     hom
    0.60
     tứ
    0.60
    omit
    0.59
    POSITIVE LOGITS
     સાં
    0.77
     starost
    0.75
     প্রতিক্রি
    0.72
    複雜
    0.72
     Cultura
    0.71
     toroidal
    0.71
    üt
    0.70
     compleja
    0.70
     kurzen
    0.69
    Clearly
    0.68
    Act Density 0.000%

    No Known Activations