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

    Neuronpedia

    INDEX
    Explanations

    aggregate structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depl
    1.62
     duelo
    1.57
     aggrieved
    1.55
    चीत
    1.55
    开展
    1.53
    在国内
    1.53
    oléon
    1.50
     défendre
    1.50
    ⊠
    1.49
    oeste
    1.49
    POSITIVE LOGITS
    a
    1.50
    ія
    1.34
    ت
    1.32
    ા
    1.31
    ు
    1.30
    া
    1.28
    รรม
    1.25
     з
    1.25
     ма
    1.23
     sap
    1.16
    Act Density 0.000%

    No Known Activations