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

    Neuronpedia

    INDEX
    Explanations

    side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proprietors
    0.81
     profits
    0.80
    ipl
    0.77
     prints
    0.77
    profits
    0.77
     tyres
    0.77
     Profits
    0.76
     pharmaceuticals
    0.75
     ibn
    0.74
    董
    0.74
    POSITIVE LOGITS
    жды
    0.82
    𝓪
    0.80
    ма
    0.74
    א
    0.71
     veces
    0.71
     batal
    0.71
     Naciones
    0.71
    END
    0.70
    еты
    0.70
    اشت
    0.70
    Act Density 0.000%

    No Known Activations