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

    Neuronpedia

    INDEX
    Explanations

    options and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /
    0.19
    nThe
    0.18
     。
    0.17
     ;
    0.17
     ।
    0.17
    n
    0.17
          
    0.17
    nYou
    0.17
    from
    0.16
    jda
    0.16
    POSITIVE LOGITS
     विकल्प
    0.24
     contender
    0.24
     choices
    0.23
     contenders
    0.22
     options
    0.21
     seçenek
    0.21
    的情况
    0.21
     situação
    0.20
     സാഹചര്യ
    0.20
     situazioni
    0.20
    Act Density 0.270%

    No Known Activations