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

    Neuronpedia

    INDEX
    Explanations

    preparedness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     інші
    0.30
    ೬
    0.30
    פ
    0.29
    Vous
    0.29
    YEAR
    0.29
    𝗨
    0.29
    Ყ
    0.29
    סי
    0.28
    écies
    0.28
    ೪
    0.28
    POSITIVE LOGITS
     waiting
    0.34
     pre
    0.34
     ready
    0.32
    但是在
    0.31
     preparada
    0.30
     but
    0.30
     prepared
    0.30
     Prepared
    0.30
     strapped
    0.30
     pero
    0.30
    Act Density 0.000%

    No Known Activations