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

    Neuronpedia

    INDEX
    Explanations

    oils and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Olive
    0.93
    Olive
    0.88
     olive
    0.77
    olive
    0.70
     Grease
    0.68
     greasy
    0.67
     olives
    0.65
    Oliv
    0.59
    橄
    0.58
     oliva
    0.57
    POSITIVE LOGITS
     extracts
    0.67
     extract
    0.64
    extract
    0.57
    提取
    0.55
     Extract
    0.54
     Extracts
    0.54
     extracted
    0.53
     extracting
    0.52
    Extract
    0.52
     추출
    0.51
    Act Density 0.010%

    No Known Activations