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

    Neuronpedia

    INDEX
    Explanations

    business processes and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Souza
    0.56
     but
    0.55
     warnings
    0.54
    之类的
    0.53
     （
    0.53
     asthma
    0.51
     longs
    0.51
     bør
    0.51
     disagrees
    0.51
     sugary
    0.50
    POSITIVE LOGITS
    Lift
    0.63
    থিত
    0.59
    Vari
    0.59
     समस्त
    0.58
    ставля
    0.57
     আধুনিক
    0.55
    Тех
    0.54
    সমূ
    0.54
     كافة
    0.54
    ceğine
    0.53
    Act Density 0.000%

    No Known Activations