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

    Neuronpedia

    INDEX
    Explanations

    inspired by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getCql
    0.52
    aways
    0.50
     trì
    0.45
    ürn
    0.45
     faites
    0.44
    zzles
    0.44
    óta
    0.44
    ern
    0.43
     Dal
    0.43
     bệnh
    0.43
    POSITIVE LOGITS
    Compensation
    0.47
     profundidad
    0.47
    、
    0.46
    ，
    0.46
     divider
    0.45
    compensation
    0.45
     частично
    0.44
    Job
    0.44
    Qualifications
    0.43
     substitution
    0.43
    Act Density 0.001%

    No Known Activations