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

    Neuronpedia

    INDEX
    Explanations

    Peter Quigley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EXPECT
    -0.78
     Hacienda
    -0.77
     cgi
    -0.77
    Bears
    -0.76
     HASH
    -0.75
     UMA
    -0.74
    zał
    -0.71
     Calvert
    -0.71
    र्श
    -0.70
    FOS
    -0.70
    POSITIVE LOGITS
    REQUIRE
    1.07
     requirement
    1.06
     REQUIRE
    0.99
    SECTION
    0.87
     requirements
    0.86
    hör
    0.85
    CHECK
    0.83
     caixas
    0.82
    ingway
    0.80
     Requirement
    0.79
    Act Density 0.031%

    No Known Activations