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

    Neuronpedia

    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    man
    0.45
     tombs
    0.45
     পরিত্যাগ
    0.45
    ினான்
    0.44
    全体の
    0.44
    腎
    0.42
    セット
    0.41
     palabras
    0.41
    どのように
    0.41
     giudice
    0.41
    POSITIVE LOGITS
    }
    0.46
    饿
    0.45
    νού
    0.45
    纱
    0.44
    촉
    0.44
     发
    0.43
     để
    0.43
     aby
    0.42
     chipset
    0.42
     Dự
    0.41
    Act Density 0.012%

    No Known Activations