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

    Neuronpedia

    INDEX
    Explanations

    Legal appeals

    np_max-act · gemini-2.0-flash

    This neuron detects language typical of legal appeals argument sections—phrases enumerating issues and asserting that the trial court erred.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Boulevard
    -0.07
    _TARGET
    -0.07
    ares
    -0.06
    ordinated
    -0.06
     instantiation
    -0.06
    -public
    -0.06
    all
    -0.06
     Morg
    -0.06
     Bullet
    -0.06
     Blvd
    -0.06
    POSITIVE LOGITS
     unus
    0.07
     kys
    0.06
    leniyor
    0.06
    xCA
    0.06
     Escorts
    0.06
     WebGL
    0.06
    ubernetes
    0.06
    (raw
    0.06
    对
    0.06
    ें।↵
    0.06
    Act Density 0.015%

    No Known Activations