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

    Neuronpedia

    INDEX
    Explanations

    each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    恐怕
    0.47
    你应该
    0.40
     sovere
    0.38
    شم
    0.37
     persecuted
    0.37
     solltest
    0.37
    ungkinan
    0.35
     disgraceful
    0.35
     obsess
    0.35
    شار
    0.35
    POSITIVE LOGITS
     Each
    0.94
    Each
    0.91
     each
    0.87
    每个
    0.74
    each
    0.72
     प्रत्येक
    0.70
     প্রতিটি
    0.69
     каждой
    0.69
     каждое
    0.69
     каждого
    0.68
    Act Density 0.031%

    No Known Activations