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

    Neuronpedia

    INDEX
    Explanations

    completely "free"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offline
    0.78
     செயற்க
    0.75
     Closed
    0.70
     closed
    0.68
     menutup
    0.68
    收
    0.68
    ጠቃ
    0.64
     комплекс
    0.64
    整数
    0.64
     domestic
    0.64
    POSITIVE LOGITS
     freedom
    2.43
     liberdade
    2.27
     libertad
    2.21
     freedoms
    2.20
    Freedom
    2.15
     libertà
    2.11
    freedom
    2.09
     liberté
    2.07
     Freedom
    2.03
     freeing
    2.01
    Act Density 1.079%

    No Known Activations