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

    Neuronpedia

    INDEX
    Explanations

    selection and specific instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كافة
    0.54
     procedures
    0.53
     multitudes
    0.52
     các
    0.52
     nejsou
    0.51
     methods
    0.50
    あらゆる
    0.50
     factors
    0.50
     शास
    0.49
     zaken
    0.49
    POSITIVE LOGITS
     intitulé
    0.87
     Strawberry
    0.86
     berjudul
    0.80
     intitul
    0.80
     piccola
    0.80
     meinem
    0.79
    rawberry
    0.79
    今年
    0.78
     ukulele
    0.77
    Projeto
    0.77
    Act Density 0.010%

    No Known Activations