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

    Neuronpedia

    INDEX
    Explanations

    loyalty and devotion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.24
    ر
    1.14
     deporte
    1.14
     neigh
    1.03
     ail
    1.01
     pregnancies
    0.98
     deportes
    0.97
    ম
    0.97
    ें
    0.95
     nėra
    0.93
    POSITIVE LOGITS
    гка
    1.05
    giver
    0.94
     setia
    0.84
    icularly
    0.79
    increasing
    0.78
     ergeben
    0.77
    𝘶
    0.77
    pecific
    0.75
    fir
    0.75
    itemView
    0.74
    Act Density 0.089%

    No Known Activations