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

    Neuronpedia

    INDEX
    Explanations

    biological processes, times, or fundamental concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.68
     आप
    0.63
    т
    0.53
    You
    0.50
    你
    0.50
     class
    0.49
     required
    0.47
    润
    0.46
    潤
    0.46
     any
    0.46
    POSITIVE LOGITS
    musik
    0.57
     muzy
    0.50
     نفسی
    0.49
     င
    0.47
    "".
    0.46
    ımız
    0.46
     debemos
    0.45
     queridos
    0.44
     musik
    0.43
     yeter
    0.43
    Act Density 0.002%

    No Known Activations