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

    Neuronpedia

    INDEX
    Explanations

    foundation for technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urring
    0.46
    ur
    0.46
    eday
    0.45
    phalodes
    0.45
    iis
    0.44
    chwitz
    0.44
    orescent
    0.43
    PerHour
    0.43
     서
    0.42
    field
    0.42
    POSITIVE LOGITS
     a
    0.55
     DATA
    0.52
     vele
    0.48
    лы
    0.47
     Global
    0.46
     khá
    0.45
     それぞれ
    0.45
    الم
    0.44
    וד
    0.43
     Data
    0.42
    Act Density 0.000%

    No Known Activations