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

    Neuronpedia

    INDEX
    Explanations

    references to church hierarchy and leaving the church.

    oai_token-act-pair · gemini-2.0-flash

    religion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.95
     насељу
    -0.85
    SourceChecksum
    -0.81
     Roskov
    -0.76
     समीक्षक
    -0.75
    SharedDtor
    -0.73
    IsMutable
    -0.73
    MigrationBuilder
    -0.71
    ंदीखरीदारी
    -0.71
    aarrggbb
    -0.68
    POSITIVE LOGITS
     I
    0.48
     OK
    0.46
     sy
    0.45
     Con
    0.45
     No
    0.45
     grand
    0.45
     M
    0.45
     W
    0.44
     кон
    0.44
    dolu
    0.43
    Act Density 0.389%

    No Known Activations