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

    Neuronpedia

    INDEX
    Explanations

    starts with or contains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oni
    0.48
    マンション
    0.47
    Pension
    0.46
    플
    0.46
     interstitiis
    0.45
     약
    0.44
    पोरेशन
    0.44
    <unused43>
    0.44
    άν
    0.43
    ဆက်
    0.42
    POSITIVE LOGITS
     воро
    0.55
    ى
    0.55
     گا
    0.51
     viewer
    0.49
    a
    0.47
    ులు
    0.46
     \
    0.46
     catcher
    0.46
     skewers
    0.45
     academic
    0.44
    Act Density 0.001%

    No Known Activations