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

    Neuronpedia

    INDEX
    Explanations

    oil spills and pollution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أنّ
    0.53
     औसत
    0.51
    😏
    0.51
    ren
    0.50
     कैल्शियम
    0.50
    颯
    0.50
     คณิต
    0.50
    😍😍
    0.49
     checkBox
    0.49
     😍
    0.49
    POSITIVE LOGITS
     oil
    0.70
     OIL
    0.66
     нефте
    0.62
    油
    0.61
     Oil
    0.61
     grease
    0.61
     petroleum
    0.58
    オイル
    0.57
     Oilers
    0.57
     out
    0.56
    Act Density 0.006%

    No Known Activations