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

    Neuronpedia

    INDEX
    Explanations

    defense with attorneys or security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     y
    0.44
     cer
    0.43
     super
    0.43
     PE
    0.41
     dop
    0.41
     finde
    0.40
    发出
    0.40
     om
    0.39
    嵘
    0.39
     conserved
    0.38
    POSITIVE LOGITS
     دفاع
    0.78
     defensive
    0.73
     defens
    0.71
    against
    0.70
     defesa
    0.69
     Defensive
    0.66
     defence
    0.65
     defending
    0.64
     defend
    0.64
     défendre
    0.64
    Act Density 0.025%

    No Known Activations