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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas or equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ',
    0.83
    只有
    0.79
     is
    0.77
    这样
    0.76
    namely
    0.75
     consiste
    0.75
     only
    0.75
    }--\
    0.74
    --
    0.74
     seems
    0.73
    POSITIVE LOGITS
    Ϳ
    0.96
    ังกฤษ
    0.95
     GDPPC
    0.92
     Ratio
    0.90
     Divorce
    0.88
     Literacy
    0.84
    )”
    0.83
     historischen
    0.82
     Jurisdiction
    0.82
    )^(
    0.82
    Act Density 0.241%

    No Known Activations