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

    Neuronpedia

    INDEX
    Explanations

    I can or cannot do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.20
     Talent
    1.08
     EPC
    1.07
     vii
    1.06
     performance
    1.05
     DV
    1.04
     perform
    1.03
     VIP
    1.02
     AED
    1.02
     Priv
    1.01
    POSITIVE LOGITS
    bahan
    1.39
    établissement
    1.36
    ripción
    1.33
    ión
    1.29
     ಇಸ್ಕೊ
    1.29
    Nếu
    1.29
    Jeśli
    1.27
    lake
    1.27
    Якщо
    1.25
    Ĵ
    1.25
    Act Density 0.047%

    No Known Activations