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

    Neuronpedia

    INDEX
    Explanations

    explanations of exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sesuai
    0.32
    て
    0.32
    
    0.32
     ModelState
    0.32
     ")");
    0.31
    ています
    0.31
    udo
    0.30
    WIDTH
    0.30
     DIVISION
    0.30
    Koordin
    0.29
    POSITIVE LOGITS
     ტ
    0.37
     bans
    0.37
     JavaBeans
    0.35
     banning
    0.34
     cazul
    0.34
     ജെ
    0.34
    CSc
    0.33
     சிங்க
    0.33
    :‏
    0.33
     жаса
    0.33
    Act Density 0.002%

    No Known Activations