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

    Neuronpedia

    INDEX
    Explanations

    structured text, DAX variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    การ
    2.43
    ский
    2.12
    с
    1.96
    व
    1.95
    వ
    1.81
     ​​
    1.80
    тые
    1.77
    е
    1.77
    ve
    1.76
    rine
    1.73
    POSITIVE LOGITS
    intellij
    1.97
     anode
    1.93
    üedad
    1.88
    ?>
    1.88
    iation
    1.85
    ൻ
    1.84
     manera
    1.82
    к
    1.82
    ের
    1.81
    ió
    1.80
    Act Density 0.001%

    No Known Activations