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

    Neuronpedia

    INDEX
    Explanations

    words starting with Con

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    āyaṇa
    0.37
    歪
    0.37
    鐙
    0.36
    樘
    0.36
    뿯
    0.36
    啵
    0.35
    இய
    0.35
    ään
    0.35
    刈
    0.35
    排除
    0.35
    POSITIVE LOGITS
     Con
    0.79
    Con
    0.75
     コン
    0.71
    con
    0.71
     Conrad
    0.71
    คอน
    0.68
     Conor
    0.68
     CON
    0.65
     Connie
    0.64
     Conquer
    0.64
    Act Density 0.011%

    No Known Activations