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

    Neuronpedia

    INDEX
    Explanations

    instruments of persuasion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𐰤
    0.43
     лаборатор
    0.42
     复
    0.42
     épars
    0.40
     복
    0.39
    illère
    0.39
    柰
    0.39
     સફળ
    0.38
    复
    0.38
     প্রফেসর
    0.38
    POSITIVE LOGITS
     pre
    0.48
     morning
    0.47
    month
    0.46
     month
    0.44
     week
    0.43
     inst
    0.41
     mist
    0.41
     und
    0.40
     habits
    0.40
     mosaics
    0.40
    Act Density 0.000%

    No Known Activations