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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Демографія
    -0.85
     مرئيه
    -0.66
     épar
    -0.65
    usercontent
    -0.64
    évaluateur
    -0.61
     تانيه
    -0.60
     esperienza
    -0.60
    Personendaten
    -0.59
     compét
    -0.59
     engraçadas
    -0.59
    POSITIVE LOGITS
     plate
    0.68
    plate
    0.52
     code
    0.52
     located
    0.47
     legend
    0.47
     panel
    0.47
     notice
    0.47
     las
    0.47
     location
    0.46
     st
    0.46
    Act Density 0.000%

    No Known Activations