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

    Neuronpedia

    INDEX
    Explanations

    specific usage or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reuses
    0.43
    britannien
    0.42
     assass
    0.39
    чне
    0.39
    뚱
    0.38
    fie
    0.38
    ॉर्डिंग
    0.38
    ୍କ
    0.37
    ੍ਹ
    0.37
    हाबाद
    0.37
    POSITIVE LOGITS
     विप
    0.41
     middleware
    0.38
    ள
    0.38
     coupled
    0.37
     servlet
    0.36
     kullanılır
    0.36
     XLS
    0.35
    不能
    0.35
    Usage
    0.35
     இயக்க
    0.35
    Act Density 0.001%

    No Known Activations