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

    Neuronpedia

    INDEX
    Explanations

    criminals pose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cultivate
    0.47
     cowork
    0.45
     Fitbit
    0.45
     upgrade
    0.42
     “
    0.42
     bundling
    0.42
     run
    0.41
     code
    0.41
     fintech
    0.40
     (“
    0.40
    POSITIVE LOGITS
    蝟
    0.44
    Manisha
    0.43
    źnie
    0.42
    akhir
    0.42
    Maharashtra
    0.41
    Chhattisgarh
    0.41
    ogenic
    0.40
     آمد
    0.40
    ﻵ
    0.40
     වශයෙන්
    0.39
    Act Density 0.012%

    No Known Activations