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

    Neuronpedia

    INDEX
    Explanations

    computer code and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gatt
    0.43
     filo
    0.38
    ilo
    0.37
    生物
    0.36
     Xbox
    0.36
    原理
    0.36
     முற
    0.35
    thio
    0.35
    undas
    0.35
     צריך
    0.34
    POSITIVE LOGITS
    businesses
    0.43
    ີ່ມ
    0.41
    Businesses
    0.39
    iseach
    0.39
    blusas
    0.39
    ată
    0.38
    timezone
    0.38
    ліся
    0.38
    नल
    0.37
    reflect
    0.37
    Act Density 0.000%

    No Known Activations