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

    Neuronpedia

    INDEX
    Explanations

    time and location prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल
    0.37
    letal
    0.37
    ل
    0.36
     Tidal
    0.36
    لت
    0.35
     Honey
    0.35
     Iwas
    0.35
    你
    0.35
    本
    0.35
     Massacre
    0.34
    POSITIVE LOGITS
    きた
    0.42
     каждом
    0.37
     każdym
    0.37
     everytime
    0.37
     опреде
    0.35
     هنگام
    0.34
    ați
    0.34
     Lorsque
    0.34
    ాయని
    0.33
    ందని
    0.33
    Act Density 0.004%

    No Known Activations