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

    Neuronpedia

    INDEX
    Explanations

    dismissed

    np_max-act · gemini-2.0-flash

    The neuron detects procedural dismissal language in legal opinions, especially phrases about an appeal being “dismissed” (often for lack of jurisdiction or want of prosecution).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     feathers
    -0.08
    045
    -0.07
    议
    -0.07
    -br
    -0.06
    046
    -0.06
    ários
    -0.06
     것은
    -0.06
     менее
    -0.06
    /sbin
    -0.06
     sino
    -0.06
    POSITIVE LOGITS
    chunk
    0.07
     allocating
    0.07
    ",[
    0.06
    ọ
    0.06
    _owned
    0.06
     assessing
    0.06
    -val
    0.06
     polled
    0.06
    Throws
    0.06
     Albania
    0.06
    Act Density 0.005%

    No Known Activations