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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nellement
    0.30
    र्गत
    0.26
    凖
    0.25
     primitiva
    0.25
    뿜
    0.24
    Kid
    0.24
     ټینس
    0.24
    Concern
    0.24
    SecurityCenter
    0.24
    ድግዳ
    0.24
    POSITIVE LOGITS
    0
    0.56
     hundred
    0.54
     puluh
    0.48
    5
    0.45
    hundred
    0.43
     dozen
    0.41
    ０
    0.41
     hundreds
    0.39
     fifty
    0.39
    десят
    0.39
    Act Density 0.177%

    No Known Activations