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

    Neuronpedia

    INDEX
    Explanations

    explain why, not what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ..,
    0.47
     ..,
    0.45
    various
    0.43
     Various
    0.43
    гун
    0.43
    watercolor
    0.42
    sensitivity
    0.42
     দুটি
    0.42
    ramos
    0.41
    irons
    0.40
    POSITIVE LOGITS
     예측
    0.43
     ازد
    0.43
     مض
    0.43
    预测
    0.43
     durée
    0.42
     inescapable
    0.41
     zindagi
    0.41
     odby
    0.41
     ağır
    0.41
     éclat
    0.41
    Act Density 0.003%

    No Known Activations