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

    Neuronpedia

    INDEX
    Explanations

    sudo commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.84
    aus
    1.60
    Personally
    1.60
    ுங்கள்
    1.58
    ️
    1.57
    ள்ளது
    1.55
    Doch
    1.54
    og
    1.52
    ================
    1.51
    ening
    1.50
    POSITIVE LOGITS
    ᐟ
    2.05
     heater
    2.02
     aata
    2.01
    あと
    2.01
    removeClass
    2.01
     diarias
    2.00
     autoWatch
    1.97
     pstmt
    1.96
    யில
    1.93
    डमी
    1.91
    Act Density 0.004%

    No Known Activations