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

    Neuronpedia

    INDEX
    Explanations

    list or choice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sections
    0.56
    sections
    0.49
     ይህ
    0.47
     దీని
    0.46
    它是
    0.46
    Sections
    0.46
    这是一
    0.46
     isso
    0.44
     Sections
    0.44
     secciones
    0.43
    POSITIVE LOGITS
    どれ
    1.16
     どれ
    1.12
     সবগুলো
    1.08
     none
    1.02
     কোনটি
    0.96
     كلهم
    0.96
    none
    0.90
     közül
    0.90
    いずれ
    0.89
     كلها
    0.88
    Act Density 0.119%

    No Known Activations