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

    Neuronpedia

    INDEX
    Explanations

    Job

    np_max-act · gemini-2.0-flash

    The neuron is a “job” detector—it activates on occurrences of the word “job” (in titles or body text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     craw
    -0.08
    ンテ
    -0.07
     Turtle
    -0.07
    urt
    -0.07
     turtle
    -0.07
     Scripture
    -0.07
    ếu
    -0.07
    verte
    -0.07
    ATE
    -0.07
    ตะว
    -0.07
    POSITIVE LOGITS
     job
    0.15
     Job
    0.13
    jobs
    0.12
    Job
    0.11
     jobs
    0.11
     JOB
    0.10
     Jobs
    0.10
    Jobs
    0.10
    job
    0.10
    (Job
    0.09
    Act Density 0.021%

    No Known Activations