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

    Neuronpedia

    INDEX
    Explanations

    BigQuery queries and datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usingCamera
    0.44
     desigual
    0.41
     अभाव
    0.39
    <unused75>
    0.39
     منظ
    0.38
    SqlServer
    0.38
     divulge
    0.38
    단체
    0.38
    umbre
    0.38
    doFilter
    0.37
    POSITIVE LOGITS
    Query
    0.44
     Query
    0.42
     media
    0.40
    query
    0.40
     geopolitical
    0.39
     Media
    0.38
     Side
    0.38
     query
    0.36
     partitioned
    0.36
     dataset
    0.36
    Act Density 0.005%

    No Known Activations