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

    Neuronpedia

    INDEX
    Explanations

    family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cer
    0.40
     râ
    0.40
    ناد
    0.39
    ޫ
    0.38
     nag
    0.38
     آب
    0.38
     sad
    0.37
     وتش
    0.37
     استاد
    0.37
     flute
    0.36
    POSITIVE LOGITS
     uncles
    0.66
     aunts
    0.64
     nieces
    0.62
     aunt
    0.60
     Cousin
    0.59
     uncle
    0.59
     Uncle
    0.57
     Aunt
    0.56
     cousins
    0.55
     niece
    0.52
    Act Density 0.134%

    No Known Activations