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

    Neuronpedia

    INDEX
    Explanations

    possessives and plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     científicos
    0.34
     parámetros
    0.32
     tecnológicos
    0.31
     ljudi
    0.31
     pasan
    0.30
     químicos
    0.30
     académicos
    0.30
     แรง
    0.30
     económicos
    0.29
     juríd
    0.29
    POSITIVE LOGITS
    (
    0.26
    Y
    0.26
    R
    0.25
     및
    0.25
    P
    0.24
    น
    0.24
    A
    0.24
    B
    0.23
    },
    0.23
    G
    0.23
    Act Density 0.453%

    No Known Activations