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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اردوش
    0.32
    bindingFields
    0.31
    reflectionMap
    0.30
     परस्मैपदी
    0.30
    র্জাতিক
    0.29
    astrous
    0.29
     ferrugineux
    0.29
    রদ্ব
    0.29
     diarrh
    0.29
     sécr
    0.28
    POSITIVE LOGITS
      
    0.35
    0.34
     a
    0.31
    ,
    0.29
    ↵
    0.29
    -
    0.29
     in
    0.29
     p
    0.27
     the
    0.27
     c
    0.26
    Act Density 1.087%

    No Known Activations