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

    Neuronpedia

    INDEX
    Explanations

    , code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сильно
    0.40
    ంది
    0.36
     হেল
    0.36
    漸
    0.35
     Hank
    0.34
    सेप्ट
    0.34
     দেবেন
    0.33
    ܘܢ
    0.33
     kulit
    0.33
     এক্সচে
    0.33
    POSITIVE LOGITS
     DRM
    0.45
     unsub
    0.44
     அனை
    0.43
     zve
    0.42
    िसू
    0.41
     onyx
    0.41
    drv
    0.40
     drum
    0.39
     Правда
    0.39
     ungroup
    0.39
    Act Density 0.001%

    No Known Activations