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

    Neuronpedia

    INDEX
    Explanations

    androidx libraries and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insoluble
    0.41
    NeedConnect
    0.39
     dechlorination
    0.39
     Calyce
    0.39
    рэ
    0.37
     whirlpool
    0.37
    γά
    0.37
     phénomènes
    0.37
    ⬯
    0.37
    gató
    0.37
    POSITIVE LOGITS
    appcompat
    0.72
    constraintlayout
    0.61
    compose
    0.58
    core
    0.55
     life
    0.54
     core
    0.53
    AppCompat
    0.53
    mult
    0.52
     Life
    0.51
     multit
    0.49
    Act Density 0.005%

    No Known Activations