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

    Neuronpedia

    INDEX
    Explanations

    expectation and hope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     опреде
    0.51
    ricting
    0.49
    $
    0.46
    ulsions
    0.44
    不僅
    0.44
     αντι
    0.44
     воин
    0.44
     шер
    0.43
    стоя
    0.43
    othiaz
    0.43
    POSITIVE LOGITS
     expectation
    1.04
    expectation
    0.95
     hope
    0.95
     expectations
    0.94
     Expectations
    0.93
     Hope
    0.91
    期待
    0.88
     HOPE
    0.84
     expectativas
    0.84
    Expect
    0.83
    Act Density 0.053%

    No Known Activations