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

    Neuronpedia

    INDEX
    Explanations

    THOUGHTS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    または
    0.38
    か
    0.38
    अगर
    0.37
     ਅਤੇ
    0.36
    め
    0.35
     אם
    0.34
    場合
    0.34
    と
    0.34
    muje
    0.33
    ák
    0.33
    POSITIVE LOGITS
     PowerPoint
    0.40
     Department
    0.36
     textbooks
    0.36
    အစိတ်အပိုင်း
    0.35
     words
    0.35
     cosmos
    0.34
     Grundlage
    0.34
     vowels
    0.34
     four
    0.33
     guardians
    0.33
    Act Density 0.000%

    No Known Activations