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

    Neuronpedia

    INDEX
    Explanations

    world saturated or dominated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pertaining
    0.51
     pertain
    0.48
    cwd
    0.44
    wasm
    0.43
    cy
    0.43
    \|^
    0.43
     maybe
    0.42
     would
    0.41
     include
    0.41
    rt
    0.41
    POSITIVE LOGITS
     riddled
    0.95
    充满了
    0.82
     rife
    0.80
     plagued
    0.77
     steeped
    0.77
    充滿
    0.77
    充满
    0.75
     brimming
    0.73
     dominated
    0.72
     Filled
    0.72
    Act Density 0.007%

    No Known Activations