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

    Neuronpedia

    INDEX
    Explanations

    anticipation and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consape
    0.47
    íte
    0.43
    Анд
    0.41
    iket
    0.41
     centímetros
    0.40
     asegurarse
    0.39
    oves
    0.39
     सल्
    0.39
     संस्कारों
    0.38
    alar
    0.38
    POSITIVE LOGITS
     expect
    0.87
    expect
    0.84
    Expect
    0.82
     Expect
    0.77
     expects
    0.74
     expecting
    0.71
    EXPECT
    0.70
     기대
    0.64
     oček
    0.63
     expected
    0.63
    Act Density 0.010%

    No Known Activations