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

    Neuronpedia

    INDEX
    Explanations

    method used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rotate
    0.71
     lå
    0.71
     tensione
    0.69
     Trilogy
    0.69
     dplyr
    0.69
     minimax
    0.68
     arp
    0.68
     Declar
    0.68
     ROWS
    0.68
    案
    0.68
    POSITIVE LOGITS
     mediums
    1.45
     methods
    1.40
     channels
    1.29
     method
    1.28
     medium
    1.26
    媒介
    1.25
    Methods
    1.23
     Methods
    1.21
    methods
    1.21
     Medium
    1.12
    Act Density 0.876%

    No Known Activations