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

    Neuronpedia

    INDEX
    Explanations

    crisis text line numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inuous
    0.38
    ченные
    0.37
     Two
    0.36
     novoProduto
    0.36
    gettags
    0.33
     السادس
    0.33
    
    0.33
    Two
    0.32
    тые
    0.32
    ことに
    0.32
    POSITIVE LOGITS
    ғи
    0.38
     tř
    0.38
     Dax
    0.36
    噩
    0.36
     Agosto
    0.36
    auern
    0.35
    ໄ
    0.35
    August
    0.35
    ेश्वर
    0.34
     entgegen
    0.34
    Act Density 0.003%

    No Known Activations