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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    希望能
    1.65
     hope
    1.62
    希望
    1.48
    Hope
    1.47
     Hope
    1.45
     希望
    1.43
     امید
    1.41
    hope
    1.36
     nadzie
    1.32
     hopefully
    1.29
    POSITIVE LOGITS
     호
    0.89
    ホ
    0.87
    호
    0.86
     HO
    0.86
     ho
    0.84
     sincere
    0.84
     sincerely
    0.81
     હો
    0.80
    hoi
    0.80
    ホー
    0.79
    Act Density 0.020%

    No Known Activations