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

    Neuronpedia

    INDEX
    Explanations

    what something does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೊಂದಿಗೆ
    0.30
     কথাই
    0.30
     کئی
    0.29
    ރ
    0.28
    諗
    0.28
    ージャ
    0.26
     swat
    0.26
     যথাযথ
    0.26
     শিগ
    0.26
     Sw
    0.26
    POSITIVE LOGITS
     when
    0.37
     conceptually
    0.36
     musically
    0.35
     بالضبط
    0.35
     compared
    0.34
     என்பதை
    0.34
    才能
    0.34
     internally
    0.34
    டுகிறது
    0.34
     beserta
    0.33
    Act Density 0.093%

    No Known Activations