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

    Neuronpedia

    INDEX
    Explanations

    code structure and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.40
    쾨
    0.38
    רו
    0.37
    ાઇ
    0.37
    Enfin
    0.37
     totalitarian
    0.37
    ี
    0.37
    ד
    0.36
    ЕН
    0.36
    ופ
    0.36
    POSITIVE LOGITS
     Using
    0.35
     utilizzare
    0.34
     Some
    0.34
     using
    0.33
     smaller
    0.33
     combo
    0.33
     If
    0.33
     JDBC
    0.33
     seconded
    0.33
     দ্বিতীয়
    0.32
    Act Density 0.258%

    No Known Activations