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

    Neuronpedia

    INDEX
    Explanations

    time visit request exclusive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permanecer
    0.49
     remained
    0.47
     остав
    0.46
     रहेगा
    0.44
     हटाया
    0.44
     inundated
    0.43
     信
    0.43
     الاجتماعي
    0.43
     translateX
    0.42
    ្នាក់
    0.42
    POSITIVE LOGITS
    п
    0.54
    лі
    0.53
    за
    0.49
    این
    0.48
    ิ
    0.47
    Li
    0.45
    Northern
    0.45
    тні
    0.44
    another
    0.44
    avour
    0.44
    Act Density 0.001%

    No Known Activations