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

    Neuronpedia

    INDEX
    Explanations

    tort

    np_max-act · gemini-2.0-flash

    This neuron identifies occurrences of the legal term “tort.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     shameful
    -0.07
     بای
    -0.07
    ,
↵
    -0.06
     anal
    -0.06
    CU
    -0.06
    usalem
    -0.06
     neměl
    -0.06
    /high
    -0.06
     �
    -0.06
    .listFiles
    -0.06
    POSITIVE LOGITS
     tort
    0.08
     Tort
    0.08
    ort
    0.07
     hann
    0.06
     fortified
    0.06
    ایز
    0.06
     доход
    0.06
     Earth
    0.06
    도별
    0.06
    -rated
    0.06
    Act Density 0.002%

    No Known Activations