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

    Neuronpedia

    INDEX
    Explanations

    sentence

    np_max-act · gemini-2.0-flash

    This neuron identifies mentions of judicial sentencing details (e.g. lengths of imprisonment or specific sentence terms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ARRAY
    -0.07
    cake
    -0.06
     dong
    -0.06
    たく
    -0.06
    Row
    -0.06
     Firstly
    -0.06
    \Mail
    -0.06
     joining
    -0.06
    Moving
    -0.06
     Maid
    -0.06
    POSITIVE LOGITS
    νηση
    0.07
    _COMM
    0.07
     temperatura
    0.06
     zdravot
    0.06
     VP
    0.06
    noun
    0.06
     Ρ
    0.06
    ').'
    0.06
     handle
    0.06
    ाजन
    0.06
    Act Density 0.003%

    No Known Activations