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

    Neuronpedia

    INDEX
    Explanations

    Elo rating system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HANDLER
    0.84
     Derivatives
    0.81
    erdings
    0.80
    係る
    0.79
     Stakes
    0.79
     stake
    0.79
    iggio
    0.79
    逪
    0.78
    ibley
    0.78
     ඉද
    0.77
    POSITIVE LOGITS
    True
    1.00
    Ser
    0.79
    TRUE
    0.78
    Genuine
    0.78
     true
    0.75
    Yes
    0.74
    Good
    0.74
    Som
    0.74
    Arch
    0.73
    true
    0.73
    Act Density 0.001%

    No Known Activations