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

    Neuronpedia

    INDEX
    Explanations

    hydrogen fusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    龋
    0.53
     шокола
    0.52
     акча
    0.49
    财
    0.47
    Chocolate
    0.46
    财产
    0.45
     নিদ্র
    0.44
    チョコレート
    0.43
    okolade
    0.43
     সৌন্দর্য
    0.42
    POSITIVE LOGITS
     hydrogen
    1.42
     Hydrogen
    1.30
    hydrogen
    1.25
    Hydrogen
    1.24
     हाइड्रोजन
    1.09
    水素
    1.05
     fusion
    1.04
    氢
    1.03
     fusing
    0.98
    氫
    0.98
    Act Density 0.030%

    No Known Activations