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

    Neuronpedia

    INDEX
    Explanations

    abnormal

    np_max-act · gemini-2.0-flash

    The neuron activates on terminology used in a radiology “Findings” section—particularly words signaling abnormalities, issues, and significant findings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    legal
    -0.07
     prevention
    -0.06
     shack
    -0.06
     갖
    -0.06
    ckpt
    -0.06
    bench
    -0.06
     Clerk
    -0.06
     coordination
    -0.06
    .gui
    -0.06
    develop
    -0.06
    POSITIVE LOGITS
     {}
    0.07
    :N
    0.06
     레
    0.06
    �
    0.06
     setw
    0.06
     감
    0.06
    -taking
    0.06
     trì
    0.05
    Cannot
    0.05
     lime
    0.05
    Act Density 0.024%

    No Known Activations