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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    w
    0.84
    bl
    0.79
    :
    0.76
    b
    0.74
    youtube
    0.72
    ,
    0.72
    og
    0.71
    facebook
    0.71
     mai
    0.70
      
    0.69
    POSITIVE LOGITS
     theſe
    0.98
    𒋢
    0.93
    𒋀
    0.90
     UWGM
    0.88
     Played
    0.86
     Gosudarstvennyj
    0.86
    ួត
    0.84
    <unused2054>
    0.83
     době
    0.83
     전류
    0.83
    Act Density 0.048%

    No Known Activations