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

    Neuronpedia

    INDEX
    Explanations

    booking and planning in advance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fie
    0.35
    ᒋ
    0.34
    ጺ
    0.34
     সুর
    0.33
    fie
    0.33
    (){
    0.32
    razi
    0.32
     첫
    0.32
     tex
    0.32
    fels
    0.32
    POSITIVE LOGITS
    提前
    1.79
     заранее
    1.78
     beforehand
    1.54
     미리
    1.53
     ahead
    1.42
     Ahead
    1.30
    Ahead
    1.28
    ahead
    1.27
    事前に
    1.11
    事先
    1.10
    Act Density 0.024%

    No Known Activations