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

    Neuronpedia

    INDEX
    Explanations

    sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.26
    7
    0.26
    \
    0.26
        
    0.25
    .
    0.25
    .$\
    0.23
    2
    0.23
    ु
    0.23
    ----------------
    0.22
           
    0.22
    POSITIVE LOGITS
     a
    0.24
     entsprechenden
    0.23
     سيكون
    0.22
     an
    0.22
    乃至
    0.22
    的设计
    0.21
    埶
    0.21
     promove
    0.20
    مان
    0.20
    நிலையில்
    0.20
    Act Density 0.783%

    No Known Activations