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

    Neuronpedia

    INDEX
    Explanations

    DNS services

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.65
      
    0.56
     some
    0.55
       
    0.54
     just
    0.53
     and
    0.52
     while
    0.52
        
    0.51
     essential
    0.51
     sometimes
    0.51
    POSITIVE LOGITS
    تدائي
    0.51
    𝓖
    0.46
    خستان
    0.45
    コハマ
    0.45
     Lobkovic
    0.45
     থাকিত
    0.44
    akarane
    0.44
    𝒈
    0.44
    bandSize
    0.44
    బాద్
    0.43
    Act Density 0.054%

    No Known Activations