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

    Neuronpedia

    INDEX
    Explanations

    job reporting structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hex
    0.55
     crackers
    0.51
     insects
    0.49
     histograms
    0.48
     straw
    0.48
     binary
    0.47
     beetles
    0.47
     scary
    0.47
     bugs
    0.47
     treaties
    0.47
    POSITIVE LOGITS
    職
    0.70
    职责
    0.69
     обязанности
    0.68
    职位
    0.66
    Job
    0.66
     должность
    0.66
    岗位
    0.65
     должности
    0.63
    job
    0.61
    职务
    0.60
    Act Density 0.057%

    No Known Activations