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

    Neuronpedia

    INDEX
    Explanations

    legal convictions

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of prior criminal convictions or sentencing‐related case details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Equals
    -0.06
    (host
    -0.06
     tabs
    -0.06
    ')],↵
    -0.06
     hoàn
    -0.06
     strncmp
    -0.06
    cete
    -0.06
     rfl
    -0.06
    adores
    -0.06
    symbols
    -0.06
    POSITIVE LOGITS
     cartesian
    0.07
    ?</
    0.07
     musica
    0.06
    ΕΝ
    0.06
     merry
    0.06
     переб
    0.06
    _poll
    0.06
    itational
    0.06
     nå
    0.06
    _prime
    0.06
    Act Density 0.007%

    No Known Activations