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

    Neuronpedia

    INDEX
    Explanations

    expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nonpayable
    0.68
    ariat
    0.65
    ādi
    0.65
     melalui
    0.64
     வழியாக
    0.64
    raiser
    0.64
     undetermined
    0.63
    arean
    0.62
    Ultimately
    0.62
     maupun
    0.61
    POSITIVE LOGITS
     expectations
    1.88
     expect
    1.79
     Expectations
    1.75
     Expect
    1.71
    Expect
    1.55
     expectation
    1.50
    expect
    1.50
     expectativas
    1.45
     Things
    1.42
     things
    1.40
    Act Density 0.560%

    No Known Activations