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

    Neuronpedia

    INDEX
    Explanations

    contrasting words like however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     astrolog
    0.52
     pais
    0.47
     brewery
    0.47
     laborer
    0.47
     layman
    0.46
     attorney
    0.46
     plain
    0.45
     truth
    0.45
     appe
    0.45
     nove
    0.45
    POSITIVE LOGITS
    Producto
    0.47
    Displays
    0.46
    regar
    0.46
    ᆭ
    0.46
    Cardiac
    0.45
    opportunities
    0.43
    キ
    0.43
    Product
    0.43
    Paras
    0.43
    Sustainability
    0.42
    Act Density 0.000%

    No Known Activations