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

    Neuronpedia

    INDEX
    Explanations

    processes and transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     हज़ार
    0.47
    筁
    0.45
    0.43
    د
    0.43
     والمع
    0.42
    承受
    0.42
     ẹ
    0.41
    ún
    0.41
     सनातन
    0.41
    ב
    0.41
    POSITIVE LOGITS
     puzzling
    0.46
     ideas
    0.44
     auditing
    0.43
     mystery
    0.43
     emerging
    0.43
     mysterious
    0.42
     emerges
    0.42
    语音
    0.40
     throughout
    0.40
     factions
    0.40
    Act Density 0.001%

    No Known Activations