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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash

    The neuron detects references to parties bearing or being awarded “costs” (i.e. legal‐costs language) in judicial opinions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     expose
    -0.07
     了
    -0.06
    .wav
    -0.06
     نمود
    -0.06
    вест
    -0.06
    лата
    -0.06
     frequencies
    -0.06
    osite
    -0.06
     disregard
    -0.06
    _vectors
    -0.06
    POSITIVE LOGITS
     Zack
    0.07
    conut
    0.07
     incumbent
    0.07
     recher
    0.06
     Donna
    0.06
    μον
    0.06
    Toyota
    0.06
    عي
    0.06
    рд
    0.06
    usher
    0.06
    Act Density 0.001%

    No Known Activations