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

    Neuronpedia

    INDEX
    Explanations

    references to legal processes and elements in a courtroom context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    testified truthfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    devamını
    -0.49
     antaranya
    -0.48
     AssemblyTitle
    -0.48
     <=",
    -0.48
     ainfi
    -0.47
    cauc
    -0.46
     Autorizaciones
    -0.46
    KURZBESCHREIBUNG
    -0.46
    írito
    -0.46
    Guilty
    -0.45
    POSITIVE LOGITS
     genuinely
    0.35
     genuine
    0.35
     truly
    0.35
     chi̍t
    0.35
    UnusedPrivate
    0.34
     olyan
    0.32
     high
    0.31
    SequentialGroup
    0.31
    Santis
    0.31
    〗
    0.30
    Act Density 0.138%

    No Known Activations