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

    Neuronpedia

    INDEX
    Explanations

    Economic Control or Domination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    訖
    0.46
     所以
    0.45
    ophosphate
    0.44
     nên
    0.41
     übrigens
    0.41
     fisica
    0.41
    得很
    0.41
     nhanh
    0.41
    舏
    0.41
    వు
    0.40
    POSITIVE LOGITS
    ll
    0.51
    M
    0.50
    ship
    0.48
    shire
    0.48
    roud
    0.47
     striker
    0.47
    T
    0.46
    rieb
    0.46
    rawd
    0.45
    '
    0.45
    Act Density 0.006%

    No Known Activations