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

    Neuronpedia

    INDEX
    Explanations

    similarity and difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     સિ
    0.48
    abend
    0.42
     പരിശ
    0.40
     बीते
    0.40
    टीवी
    0.38
    ressione
    0.38
    ниш
    0.38
    Zw
    0.38
     এটাই
    0.37
     Tela
    0.37
    POSITIVE LOGITS
     equally
    0.65
    同樣
    0.64
    同样
    0.61
     ebenfalls
    0.61
     similarly
    0.58
    同样的
    0.52
     igualmente
    0.51
     Equally
    0.47
     folgte
    0.46
     Similarly
    0.46
    Act Density 0.069%

    No Known Activations