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

    Neuronpedia

    INDEX
    Explanations

    complex introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     отсут
    0.50
     indicating
    0.45
     Corr
    0.45
     отсутствии
    0.43
     Spelling
    0.43
    ถูกต้อง
    0.42
     Paran
    0.41
     Form
    0.41
     pravil
    0.41
     язык
    0.40
    POSITIVE LOGITS
    embedded
    0.53
     complex
    0.51
     lengthy
    0.50
     embedded
    0.49
    複雑
    0.49
    嵌套
    0.48
     introductory
    0.48
    Embedded
    0.46
    复杂
    0.46
     complicated
    0.45
    Act Density 0.063%

    No Known Activations