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

    Neuronpedia

    INDEX
    Explanations

    explaining complex processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verão
    0.42
    ческом
    0.41
     ар
    0.41
     investigación
    0.39
     Fälle
    0.39
     expansión
    0.38
     generalised
    0.37
    juven
    0.37
     கரிம
    0.37
    cler
    0.37
    POSITIVE LOGITS
    客
    0.38
    有些人
    0.37
     roughly
    0.37
    合理
    0.37
    線
    0.36
     อาจ
    0.36
     něco
    0.35
     কারও
    0.35
     may
    0.35
     বহ
    0.34
    Act Density 0.006%

    No Known Activations