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

    Neuronpedia

    INDEX
    Explanations

    Developing, repetitive, flatulence, maximizing advertising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MD
    0.48
     درباره
    0.45
     сле
    0.45
    тни
    0.45
     жі
    0.43
    𝕞
    0.43
     Fire
    0.43
     स्त्रियों
    0.42
    iiv
    0.41
    SUP
    0.41
    POSITIVE LOGITS
    尊重
    0.48
    DejaVu
    0.47
    物
    0.43
     సందర్భ
    0.42
    重點
    0.41
    仲
    0.41
    п
    0.41
    )="
    0.41
    zhang
    0.40
    상은
    0.39
    Act Density 0.000%

    No Known Activations