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

    Neuronpedia

    INDEX
    Explanations

    often associated with fame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afforded
    0.47
     designee
    0.45
     deemed
    0.44
    sched
    0.44
    裨
    0.42
     refusal
    0.42
    ೀಲ
    0.42
     deems
    0.42
    scheduled
    0.40
    advant
    0.40
    POSITIVE LOGITS
     famoso
    0.98
     famously
    0.97
     знамени
    0.96
     famous
    0.96
     berühm
    0.96
     familiar
    0.94
     famosa
    0.91
     iconic
    0.90
     유명
    0.88
     مشہور
    0.87
    Act Density 0.691%

    No Known Activations