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

    Neuronpedia

    INDEX
    Explanations

    to expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     According
    0.73
     आपल्या
    0.70
     When
    0.70
     Whenever
    0.68
     atunci
    0.67
     Instead
    0.66
     juist
    0.66
    మిక
    0.65
     nachdem
    0.65
     eigenlijk
    0.64
    POSITIVE LOGITS
     expect
    1.69
    Expect
    1.41
     expects
    1.33
    expect
    1.33
     Expect
    1.31
     expectations
    1.27
     expectation
    1.20
     prepare
    1.13
     EXPECT
    1.11
     anticipate
    1.08
    Act Density 0.550%

    No Known Activations