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

    Neuronpedia

    INDEX
    Explanations

    text referring to international law and treaties, including non-English terms

    oai_token-act-pair · gemini-2.0-flash

    Legal terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.75
     Мексичка
    -0.69
     defaultstate
    -0.66
    NUMX
    -0.60
    يميديا
    -0.60
    évaluateur
    -0.59
     CGPoint
    -0.57
    fscanf
    -0.56
    offsetof
    -0.56
    ]")]
    -0.55
    POSITIVE LOGITS
     Jurí
    0.56
     civiles
    0.52
    nachweis
    0.51
     judiciales
    0.49
     Privacidade
    0.48
     jurí
    0.47
    λά
    0.47
    anyi
    0.46
    tryck
    0.46
     discri
    0.45
    Act Density 1.657%

    No Known Activations