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

    Neuronpedia

    INDEX
    Explanations

    hope and hope for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uğ
    0.45
    ểm
    0.43
    veled
    0.42
    igkeit
    0.41
    osi
    0.40
    т
    0.40
    ėjo
    0.39
    ourcing
    0.38
    üğ
    0.38
    atürk
    0.37
    POSITIVE LOGITS
     hope
    0.63
     hoping
    0.62
     to
    0.62
     希望
    0.60
     Hope
    0.59
     HOPE
    0.59
     hopeful
    0.57
     Esperanza
    0.57
    希望
    0.56
     esperanza
    0.56
    Act Density 0.009%

    No Known Activations