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

    Neuronpedia

    INDEX
    Explanations

    h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beantwort
    -0.09
     entertain
    -0.08
    orderby
    -0.08
    -address
    -0.08
     unsolicited
    -0.08
     ответы
    -0.08
     pretending
    -0.08
    纪律
    -0.08
     порядок
    -0.08
     órdenes
    -0.08
    POSITIVE LOGITS
     endangered
    0.16
     habitat
    0.15
     habitats
    0.13
     Habitat
    0.12
     endemic
    0.11
     especies
    0.10
     biodiversity
    0.10
     rarity
    0.10
    Protected
    0.09
     species
    0.09
    Act Density 0.037%

    No Known Activations