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

    Neuronpedia

    INDEX
    Explanations

    job description and training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.39
    。
    0.35
    ﺰ
    0.34
    ।
    0.34
    .
    0.32
    م
    0.31
    ม
    0.30
    2
    0.29
    ﺪ
    0.29
    4
    0.28
    POSITIVE LOGITS
     jobs
    0.39
     JOB
    0.39
     Job
    0.38
     employment
    0.38
     stints
    0.36
     wages
    0.36
     Employment
    0.35
     salarié
    0.35
    就业
    0.34
    职工
    0.34
    Act Density 0.410%

    No Known Activations