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

    Neuronpedia

    INDEX
    Explanations

    code snippets and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ので
    1.98
    可以
    1.93
    Те
    1.89
     gren
    1.77
     arrondies
    1.76
    这意味着
    1.76
    Gruß
    1.72
     아닌
    1.72
     Anzahl
    1.70
    oer
    1.69
    POSITIVE LOGITS
     dignity
    1.60
    th
    1.58
    worthiness
    1.58
     Bankers
    1.55
     тех
    1.51
    هم
    1.48
    nud
    1.47
     ATMs
    1.47
    ым
    1.47
    Highest
    1.45
    Act Density 0.000%

    No Known Activations