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

    Neuronpedia

    INDEX
    Explanations

    programming languages and this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    などの
    0.40
     secretly
    0.38
    noduch
    0.38
    गेड
    0.37
    などを
    0.37
     membeli
    0.37
     fossero
    0.37
     없고
    0.36
    lash
    0.35
     kahit
    0.35
    POSITIVE LOGITS
    입니다
    0.48
    합니다
    0.41
    ):
    0.38
     этой
    0.37
     của
    0.37
     هذا
    0.36
     this
    0.36
     цієї
    0.35
     này
    0.34
     этого
    0.32
    Act Density 0.000%

    No Known Activations