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

    Neuronpedia

    INDEX
    Explanations

    reasons, explanations, or subsequent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iembre
    0.48
    يلي
    0.47
    𝙋
    0.47
     Agile
    0.46
     aimed
    0.46
    сион
    0.45
     Drinfeld
    0.45
    iędzy
    0.45
     commerciales
    0.44
     i
    0.44
    POSITIVE LOGITS
     Tuti
    0.47
    '
    0.47
    ératures
    0.46
    ូប
    0.45
    paran
    0.45
    確かに
    0.45
    urar
    0.45
    籬
    0.44
     passar
    0.44
     nons
    0.43
    Act Density 0.000%

    No Known Activations