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

    Neuronpedia

    INDEX
    Explanations

    math calculations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feedstock
    0.77
     DQN
    0.73
     SoundCloud
    0.72
     FAQ
    0.72
     plen
    0.71
     múltiples
    0.71
     NDVI
    0.71
     hyperplane
    0.71
     PvP
    0.71
     DevOps
    0.70
    POSITIVE LOGITS
    9
    1.32
    0
    1.30
    8
    1.25
    6
    1.23
    7
    1.23
    4
    1.21
    5
    1.18
    2
    1.17
    3
    1.16
    1
    1.05
    Act Density 0.669%

    No Known Activations