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

    Neuronpedia

    INDEX
    Explanations

    shaving tools and supplies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जूस
    0.45
     ep
    0.40
     deleteTask
    0.40
    陏
    0.39
     pierce
    0.38
     Clip
    0.38
     Kee
    0.38
     pat
    0.38
    洗衣
    0.38
     Spell
    0.38
    POSITIVE LOGITS
     safety
    0.55
    safety
    0.55
     lather
    0.55
     brushes
    0.50
    Safety
    0.49
     brush
    0.47
     brushless
    0.47
    brushes
    0.47
     सेफ्टी
    0.46
     strop
    0.46
    Act Density 0.004%

    No Known Activations