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

    Neuronpedia

    INDEX
    Explanations

    List items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rupees
    0.42
     जिनमें
    0.39
     रिंग
    0.38
     दिशा
    0.38
    組成
    0.38
    ल्
    0.37
    ะนั้น
    0.37
    aaa
    0.36
     전부
    0.36
     निर्माण
    0.36
    POSITIVE LOGITS
    ുമോ
    0.41
    เก็บ
    0.38
     obicei
    0.37
    iseach
    0.36
    ystore
    0.36
    ubro
    0.36
     cris
    0.36
    strom
    0.36
    бург
    0.36
     Cris
    0.35
    Act Density 0.002%

    No Known Activations