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

    Neuronpedia

    INDEX
    Explanations

    around time references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     él
    0.74
    LEMENT
    0.73
     danger
    0.73
     五
    0.72
     gele
    0.72
     నేపథ
    0.71
     단
    0.71
     MÉ
    0.71
     할
    0.70
     二
    0.70
    POSITIVE LOGITS
    与其
    0.75
    เดียวกัน
    0.72
    reaction
    0.71
     rspace
    0.68
    cześ
    0.68
    almost
    0.68
    érateur
    0.68
    довж
    0.67
    setObjectName
    0.66
    いっぱい
    0.66
    Act Density 0.482%

    No Known Activations