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

    Neuronpedia

    INDEX
    Explanations

    runes, explic, Pre, send

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.89
    ll
    0.84
    ss
    0.84
    മുണ്ട
    0.81
    sc
    0.80
    vra
    0.77
    ringen
    0.76
    d
    0.76
    rit
    0.75
    alom
    0.75
    POSITIVE LOGITS
    额
    0.74
    チーム
    0.72
     thậm
    0.70
    ０
    0.68
    িং
    0.67
     leucine
    0.67
     Índice
    0.66
     світ
    0.65
    移
    0.65
    ց
    0.64
    Act Density 0.005%

    No Known Activations