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

    Neuronpedia

    INDEX
    Explanations

    thank you for your time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     okam
    0.75
    ...).
    0.74
    …
    0.74
     direct
    0.71
    ...
    0.71
     blank
    0.68
     immediate
    0.67
     unique
    0.66
     …
    0.66
     instant
    0.65
    POSITIVE LOGITS
    혐
    1.00
    更加
    0.92
     부분
    0.91
    我的
    0.90
    Saya
    0.90
     मुझे
    0.89
    avorites
    0.89
    私の
    0.89
    我已经
    0.88
    Tôi
    0.88
    Act Density 0.171%

    No Known Activations