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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    Ansible playbooks and related configuration code for automating tasks.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on YAML list-item markers (the leading “-” tokens indicating list entries).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Harvard
    -0.06
    .return
    -0.06
    ODE
    -0.06
     Fri
    -0.06
    ASON
    -0.06
    293
    -0.06
     FILE
    -0.05
     Carson
    -0.05
    .uuid
    -0.05
    notes
    -0.05
    POSITIVE LOGITS
     bv
    0.07
    �
    0.07
    -serving
    0.07
     rád
    0.07
     Journalism
    0.06
    บาท
    0.06
     assignable
    0.06
     видов
    0.06
     shalt
    0.06
    ۱۰
    0.06
    Act Density 0.002%

    No Known Activations