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

    Neuronpedia

    INDEX
    Explanations

    to be able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peered
    0.45
     risultato
    0.40
    єш
    0.40
     län
    0.40
    utis
    0.40
     両
    0.40
    ারিত
    0.39
     層
    0.39
    চূ
    0.39
    係
    0.39
    POSITIVE LOGITS
    こちらの
    0.39
     accomplish
    0.39
     사랑
    0.38
    Игра
    0.38
     excell
    0.37
     రచ
    0.37
    ॥
    0.37
     turmeric
    0.37
     minimalistic
    0.37
     choline
    0.37
    Act Density 0.006%

    No Known Activations