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

    Neuronpedia

    INDEX
    Explanations

    explaining itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AND
    0.41
    O
    0.37
     and
    0.36
     More
    0.35
     Diversity
    0.35
    改めて
    0.35
     continuing
    0.34
    <h3>
    0.34
     melanjutkan
    0.33
     Cand
    0.32
    POSITIVE LOGITS
    𝗂
    0.49
    劷
    0.47
    lepší
    0.45
     inactivació
    0.44
    illé
    0.44
     ہوسک
    0.44
    出来ます
    0.44
     într
    0.43
     можуть
    0.43
    答应
    0.43
    Act Density 0.013%

    No Known Activations