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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ገ
    0.33
     meriye
    0.33
     suppressor
    0.33
    LogRow
    0.32
     demikian
    0.31
    albumin
    0.31
    로서
    0.31
    E
    0.30
    ();
    0.30
    nante
    0.30
    POSITIVE LOGITS
    پیش
    0.30
     iced
    0.29
     Ahead
    0.29
     encro
    0.28
     Times
    0.28
     Action
    0.28
    ໃຫ້
    0.28
     SEA
    0.28
     پیش
    0.27
     Shores
    0.27
    Act Density 0.015%

    No Known Activations