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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    1.00
     interpretation
    0.90
     progression
    0.89
     technique
    0.89
     measurement
    0.89
     tips
    0.88
    特点
    0.88
    completion
    0.88
    Tips
    0.88
    estimator
    0.88
    POSITIVE LOGITS
     на
    1.11
     on
    0.95
     On
    0.94
     på
    0.92
     Onc
    0.86
     على
    0.85
     Vapor
    0.81
     Voltaire
    0.81
    ској
    0.80
     საქართველოს
    0.80
    Act Density 0.000%

    No Known Activations