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

    Neuronpedia

    INDEX
    Explanations

    leads to more/fewer/greater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ied
    0.95
     behalf
    0.94
    .")
    0.87
    '
    0.84
     pertain
    0.84
     guten
    0.83
     relating
    0.82
     absolue
    0.82
     arit
    0.82
     ori
    0.81
    POSITIVE LOGITS
    siniz
    1.02
    不错的
    0.96
    更多的
    0.94
     عدم
    0.91
     ఎక్కువ
    0.89
     devastating
    0.89
     shortages
    0.87
     엄청
    0.85
    短暂
    0.85
    增加
    0.84
    Act Density 0.046%

    No Known Activations