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

    Neuronpedia

    INDEX
    Explanations

    timing and progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ថ្ល
    0.80
     recharging
    0.75
     preserved
    0.75
     Dlatego
    0.74
     سواء
    0.74
    况
    0.71
     경우가
    0.71
    优质
    0.71
     переза
    0.70
     የቀ
    0.70
    POSITIVE LOGITS
     soon
    1.80
     Soon
    1.70
    Soon
    1.70
     sooner
    1.61
     earliest
    1.58
     early
    1.54
     본격
    1.53
     eventually
    1.46
     sớm
    1.45
    soon
    1.40
    Act Density 0.156%

    No Known Activations