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

    Neuronpedia

    INDEX
    Explanations

    Poland and "goes directly"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lassen
    0.73
     zásobníku
    0.69
    வதன்
    0.67
    を通して
    0.66
    ifique
    0.65
    avant
    0.65
    mique
    0.64
    σουν
    0.63
    ungkan
    0.63
    culaire
    0.62
    POSITIVE LOGITS
     pod
    1.07
     ob
    0.98
     w
    0.97
    Pod
    0.95
    pod
    0.93
     Pod
    0.91
     pach
    0.90
     POD
    0.88
    Poland
    0.87
     pol
    0.86
    Act Density 0.062%

    No Known Activations