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

    Neuronpedia

    INDEX
    Explanations

    asking for ONE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
    Veg
    0.45
    0
    0.44
     הת
    0.42
     والك
    0.42
    istro
    0.42
    Ni
    0.41
    To
    0.41
     расти
    0.41
    acceler
    0.40
    POSITIVE LOGITS
    :
    0.47
    ؎
    0.43
     blem
    0.43
    น
    0.43
    报错
    0.42
     cavité
    0.41
     setLoading
    0.39
    彡
    0.39
     jml
    0.39
    ͗
    0.39
    Act Density 0.002%

    No Known Activations