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

    Neuronpedia

    INDEX
    Explanations

    questions about character and scenario

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    糞
    0.45
     leverages
    0.44
    鏝
    0.44
     outperforms
    0.43
     memoranda
    0.43
     contempt
    0.41
     RECEIPTS
    0.41
     econometric
    0.40
     ancillary
    0.40
     COMPOUNDS
    0.40
    POSITIVE LOGITS
     ✨
    0.82
     comfy
    0.74
     sparkly
    0.73
     fluffy
    0.73
     hehe
    0.72
    (*´
    0.70
     🥰
    0.70
    ✨
    0.70
     💕
    0.69
    💕
    0.68
    Act Density 0.220%

    No Known Activations