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

    Neuronpedia

    INDEX
    Explanations

    Centuries and decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     μόνο
    0.89
     сколько
    0.75
    नहीं
    0.73
    짜
    0.68
     perfect
    0.66
     cooldown
    0.66
     모든
    0.66
     Où
    0.65
    Dónde
    0.65
     komma
    0.65
    POSITIVE LOGITS
     jaren
    0.88
     década
    0.87
     século
    0.87
     publie
    0.86
     siglo
    0.85
     authorizes
    0.83
     decades
    0.81
     בשנת
    0.79
     affaire
    0.79
     phenomenon
    0.78
    Act Density 0.219%

    No Known Activations