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

    Neuronpedia

    INDEX
    Explanations

    go against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рија
    0.74
    SafeArea
    0.71
     Sequelize
    0.70
    при
    0.70
    wijk
    0.69
    شود
    0.69
     فح
    0.69
    ារ
    0.69
     Vamos
    0.68
    حق
    0.67
    POSITIVE LOGITS
    ्यारह
    1.05
    FundMe
    1.02
    VERN
    0.98
     bankrupt
    0.97
    against
    0.95
     saur
    0.95
     unnoticed
    0.94
    çalves
    0.93
    Against
    0.93
     searchValue
    0.93
    Act Density 0.111%

    No Known Activations