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

    Neuronpedia

    INDEX
    Explanations

    concepts of space and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Son
    0.47
     ancienne
    0.47
    US
    0.46
    ดับ
    0.46
    リ
    0.46
     June
    0.44
    Rồi
    0.44
    貅
    0.43
    Số
    0.43
     Journal
    0.42
    POSITIVE LOGITS
    ğine
    0.46
     않
    0.45
    격
    0.42
     det
    0.42
     بمع
    0.40
     측
    0.40
     طی
    0.39
     없
    0.39
     wrapper
    0.39
     تغ
    0.39
    Act Density 0.000%

    No Known Activations