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

    Neuronpedia

    INDEX
    Explanations

    releasing or releasing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jesi
    0.61
    η
    0.61
     ব্যব
    0.60
    ปลาย
    0.56
    り返
    0.56
    marshalN
    0.55
    頂いた
    0.55
     GeV
    0.55
     диагностики
    0.55
    perceptron
    0.55
    POSITIVE LOGITS
     releasing
    1.35
     release
    1.25
     releases
    1.24
    释放
    1.20
    release
    1.19
     Release
    1.18
     released
    1.16
     RELEASE
    1.13
    released
    1.07
    RELEASE
    1.06
    Act Density 0.025%

    No Known Activations