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

    Neuronpedia

    INDEX
    Explanations

    revised content, second version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     først
    0.88
    actéristiques
    0.87
    ardu
    0.85
    ptives
    0.79
     Yesus
    0.78
     lediglich
    0.76
    getConfiguration
    0.76
     består
    0.75
    出一
    0.75
    stylers
    0.75
    POSITIVE LOGITS
     II
    1.50
    II
    1.31
    2
    1.22
     Revised
    1.09
     Improved
    1.06
     improved
    1.05
    Improved
    1.05
     Revisited
    1.05
     revised
    1.04
     Again
    1.02
    Act Density 0.250%

    No Known Activations