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

    Neuronpedia

    INDEX
    Explanations

    gentle sounds and learning toys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     YouTuber
    0.43
    sG
    0.42
    ⓘ
    0.41
     playerName
    0.40
     assertTrue
    0.39
    คุณ
    0.38
     ನಿಮಗೆ
    0.38
    ప్పటి
    0.37
     YouT
    0.37
     券
    0.37
    POSITIVE LOGITS
    ot
    0.44
    ord
    0.43
    ensory
    0.42
     diciendo
    0.42
    वेदनशील
    0.42
     peoples
    0.41
    和社会
    0.41
    惦
    0.41
     वंचित
    0.41
     जिसकी
    0.41
    Act Density 0.001%

    No Known Activations